JP2019206074A - Preliminary working apparatus, working apparatus and worked condition detection device - Google Patents

Abstract

To provide a preliminary working apparatus, a working apparatus and a worked condition detection device each of which working failure such as chipping leading to defect to be detected in real time and with high degree of accuracy.SOLUTION: Machining mark change data 34 related to a machining mark is created from imaging data of the machining mark imaged with a camera 30. A vibration sensor 40 detects vibration during working of a workpiece 10 by a discoidal grindstone 4. Vibration change data 44 related to temporal change in vibration, is created from primary data 42 related to vibration detected by the vibration sensor 40. The machining mark change data 34 and vibration change data 44 are compared with each other. The machining mark change data 34 such as chipping leading to defect is associated with vibration change data 44, whereby the machining mark being failure corresponding to chipping and so son leading to defect can be determined from vibration change data 44.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a preliminary processing device, a processing device, and a processing state detection device.

  For example, in a technique of cutting a wafer or the like into individual pieces, a dicer is known as a cutting device using a rotating grindstone. For example, in cutting with a dicer, chipping (including chipping) occurs in a processing mark (kerf) such as a cutting mark. As the cause, nonconformity of cutting conditions, abrasion of a grindstone, etc. can be considered.

  Chipping exceeding a predetermined size becomes defective in an electronic component that has been cut into pieces after cutting. Conventionally, in chipping, it is common to check a wafer or the like that has been completely cut off with a microscope off-line. If chipping can be confirmed during cutting, subsequent chipping can be prevented in advance.

  Note that Patent Document 1 discloses a dicer that captures an image of a kerf that is being cut by an imaging device. However, on-line imaging of machining marks in an environment in which cutting water is constantly applied is difficult, and it is difficult to accurately detect chipping that leads to defects in real time.

Japanese Patent Laying-Open No. 2015-205388

  The present invention has been made in view of such a situation, and an object thereof is to provide a preliminary processing apparatus, a processing apparatus, and a processing state detection apparatus capable of accurately detecting a processing defect such as chipping leading to a defect in real time. It is to be.

In order to achieve the above object, a preliminary processing apparatus according to the first aspect of the present invention comprises:
A processing tool for processing the workpiece;
A drive shaft for driving the processing tool;
A holding member for holding the workpiece;
An X-axis moving mechanism for moving the holding member relative to the processing tool in the X-axis direction;
A Y-axis moving mechanism for moving the drive shaft relative to the workpiece in the Y-axis direction;
A Z-axis moving mechanism for moving the drive shaft relative to the workpiece in the Z-axis direction;
Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
Have

  The preliminary processing apparatus according to the first aspect of the present invention may include an imaging unit, but it is not necessarily required. For example, the processing trace of the workpiece by the processing tool can be imaged using an imaging unit different from the preliminary processing apparatus. Note that the preliminary processing apparatus may be the same as the actual processing apparatus, or may be a dedicated apparatus for creating data. Imaging by the imaging means may be performed after the processing, or may be performed simultaneously with the processing. In the case of performing simultaneously with the processing, the image may be taken while removing the processing liquid such as the cutting fluid or the polishing fluid, unlike the normal processing, so that the processing trace can be easily imaged by the imaging means. As a means for removing the processing liquid, means such as blowing off the processing liquid around the cutting trace so that the processing trace by the processing tool can be easily seen during the processing can be considered.

  For example, machining trace change data related to the time change of the machining trace can be created from the imaging data of the machining trace imaged by the imaging means. In addition, the vibration detection means can detect vibration during processing of the workpiece by the processing tool. Furthermore, vibration change data related to the time change of vibration can be created from the data detected by the vibration detection means.

  These correlations can be obtained by comparing the machining trace change data and the vibration change data. By associating the change data of machining traces such as chipping that leads to defects with the change data of vibrations, it is possible to judge the defect of machining traces corresponding to chipping that leads to defects from the change data of vibrations Become.

  For example, in the preliminary processing apparatus according to the first aspect of the present invention, a processing trace defect corresponding to chipping or the like leading to a defect, for example, a processing trace defect of several tens of μm or less, preferably 10 μm or less is detected from vibration change data. It becomes possible. In the past, it was possible to detect a processing defect such as chipping of about 100 μm using the detection signal of the vibration detection sensor, but a defect of a processing mark of several tens μm or less, preferably 10 μm or less, It was difficult to detect from.

  By using the correlation data between vibration change data and machining defects obtained by the preliminary machining apparatus according to the first aspect of the present invention in an actual machining apparatus, machining defects such as chipping leading to defects can be detected accurately in real time. It becomes possible.

  The comparison between the machining trace change data and the vibration change data is performed by, for example, a collating unit of a preliminary machining apparatus. Preferably, the preliminary processing apparatus obtains processing failure data corresponding to processing failure of the workpiece by the processing tool from the processing trace change data based on the correlation obtained by the collating means, and changes vibration corresponding to the processing failure data. It further has an extraction means for extracting special change data of the data.

  Preferably, when the vibration change data is equal to or greater than a threshold value, the preliminary processing apparatus determines that the processing failure of the workpiece by the processing tool has occurred, and the special change data obtained by the extraction unit. There is further provided a threshold value determining means for setting a threshold value in

  Preferably, the preliminary processing apparatus further includes storage means for storing the threshold value determined by the threshold value determination means.

The preliminary processing apparatus according to the second aspect of the present invention is:
A processing tool for processing the workpiece;
A drive shaft for driving the processing tool;
A holding member for holding the workpiece;
An X-axis moving mechanism for moving the holding member relative to the processing tool in the X-axis direction;
A Y-axis moving mechanism for moving the drive shaft relative to the workpiece in the Y-axis direction;
A Z-axis moving mechanism for moving the drive shaft relative to the workpiece in the Z-axis direction;
Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
An imaging means for imaging the workpiece trace of the workpiece by the processing tool;
Machining trace change data creating means for creating machining trace change data related to the position change of the machining trace imaged by the imaging means;
Vibration change data creating means for creating vibration change data obtained from primary data of vibration detected by the vibration detecting means;
Collating means for collating the machining trace change data with the vibration change data.

  In the preliminary processing apparatus according to the second aspect of the present invention, similar to the preliminary processing apparatus according to the first aspect of the present invention, by comparing (collating) the processing trace change data with the vibration change data, Correlation (matching result) can be obtained. By associating the change data of machining traces such as chipping that leads to defects with the change data of vibrations, it is possible to judge the defect of machining traces corresponding to chipping that leads to defects from the change data of vibrations Become.

  For example, in the preliminary processing apparatus according to the second aspect of the present invention, a processing trace defect corresponding to chipping or the like leading to a defect, for example, a processing trace defect of several tens μm or less, preferably 10 μm or less is detected from vibration change data. Discriminant criteria that make it possible to be found.

  By using correlation data between vibration change data and machining defects obtained by the preliminary machining apparatus according to the second aspect of the present invention in an actual machining apparatus, machining defects such as chipping that leads to defects can be accurately detected in real time. It becomes possible.

  The comparison (collation) between the machining mark change data and the vibration change data is performed, for example, by collation means of a preliminary machining apparatus. Preferably, the preliminary processing apparatus extracts the special change data of the vibration change data that is highly related to the processing failure of the workpiece by the processing tool based on the correlation (matching result) obtained by the matching unit. And a calculation means for calculating a discrimination criterion for finding a machining defect of the workpiece from the vibration change data.

  In the preliminary machining apparatus according to the second aspect of the present invention, the calculation means is used to indicate that, among the plural types of vibration change data, any special change data of any vibration change data is determined as to whether there is a machining defect of the workpiece. It is possible to find a discriminant criterion such as “It is possible to find whether it is directly related or not”. An example of the discrimination criterion is a logical expression of a program. In the second aspect of the present invention, it is not always necessary to provide a threshold value for the special change data.

  Preferably, the calculation means includes machine learning means for extracting the special change data and calculating a discrimination criterion by machine learning. By incorporating the machine learning means into the calculation means, it is possible to efficiently find the above-described discrimination criteria.

  Preferably, the algorithm of the machine learning means is random forest or deep learning. By using this type of machine learning means, it becomes easy to efficiently find a discrimination criterion from a large number of special change data.

  Preferably, the preliminary processing apparatus according to the second aspect of the present invention outputs a discrimination criterion storage unit that stores the discrimination criterion calculated by the arithmetic unit, and the discrimination criterion stored in the discrimination criterion storage unit. Output means. In the discriminant criterion storage means, software (program) or the like is used as a discriminant criterion (for example, a detection algorithm such as a logical expression) for “detecting special change data relating to machining defects from a large number of types of vibration change data”. Can be saved in format.

  This discrimination criterion can be output to a LAN, Internet communication means, or the like, or output to another storage device and stored. The output discriminant criteria are used in actual machining equipment, and during machining, a large variety of vibration change data is created from the detected vibration data in real time, and special change data relating to machining defects is detected from these. be able to.

  Preferably, the vibration change data creation means includes data conversion means for Fourier transforming the primary data of the vibration. By performing the Fourier transform, it becomes easy to detect special change data relating to processing defects that could not be found in the primary data of vibration.

  Preferably, the vibration change data creating means converts the primary data of the vibration at a frequency m times a predetermined reference frequency (f) (m is a natural number) using a predetermined conversion formula. Have By creating vibration change data for each of a plurality of frequencies, it becomes easy to detect special change data relating to processing defects that could not be found in the primary vibration data.

  Preferably, the data conversion means adds the primary data of the vibration to (m + 0) of the predetermined reference frequency (f) in addition to every m times (m is a natural number) of the predetermined reference frequency (f). .5) Data conversion is performed using a predetermined conversion formula every multiple (m is a natural number). With this configuration, it is easy to find a determination criterion that improves the detection accuracy of special change data related to processing defects and the like.

  Preferably, the vibration change data creating unit includes a filtering unit that performs a filtering process on the primary data of the vibration and creates noise related data indicating a relationship with the noise data. By adding noise-related data as an example of a plurality of types of vibration change data, it becomes easier to find a criterion for improving the detection accuracy of special change data related to processing defects.

  Preferably, the reference frequency is a frequency related to the movement of the processing tool. By performing data conversion at such an integral multiple of the reference frequency or an intermediate frequency between them, it becomes easy to find a determination reference that improves the detection accuracy of special change data related to processing defects.

  Preferably, the vibration change data creating means further includes window means for generating a histogram of the primary data of the vibration or the secondary data obtained from the primary data of the vibration for each predetermined range of windows. By making the vibration data into a histogram for each window, it is easy to find a criterion for improving the detection accuracy of special change data related to processing defects and the like.

  The window means overlaps adjacent windows, and histograms the primary data of the vibration or the secondary data for each window. With this configuration, it is easy to find a determination criterion that improves the detection accuracy of special change data related to processing defects and the like.

  Although it does not specifically limit as said processing tool, For example, when it is a cutting tool, it is especially effective.

The preliminary processing apparatus according to the second aspect of the present invention is:
When processing the workpiece by the processing tool, from the vibration change data obtained by the vibration detection means and the vibration change data creation means, the special change data is determined based on a determination criterion obtained by the calculation means, You may further have the discrimination means which discriminate | determines the processing state by a processing tool.

  By having the discriminating means, the preliminary processing apparatus according to the second aspect of the present invention can also be used as a normal processing apparatus as in the first aspect.

The processing apparatus according to the first aspect of the present invention is:
A processing tool for processing the workpiece;
A drive shaft for driving the processing tool;
A holding member for holding the workpiece;
An X-axis moving mechanism for moving the holding member relative to the processing tool in the X-axis direction;
A Y-axis moving mechanism for moving the drive shaft relative to the workpiece in the Y-axis direction;
A Z-axis moving mechanism for moving the drive shaft relative to the workpiece in the Z-axis direction;
Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
Comparing means for comparing vibration change data obtained from primary data of vibration detected by the vibration detecting means with data obtained by any of the preliminary processing apparatuses described above.

  Preferably, the processing tool is a cutting tool so that the workpiece can be cut, and the comparison means can detect the presence or absence of chipping of the workpiece at the cutting position of the workpiece.

  The processing apparatus according to the first aspect of the present invention may further include warning means for outputting an alarm when an abnormality is detected by the comparison means.

  Further, the machining apparatus according to the first aspect of the present invention may further include a storage unit that stores a machining position of the workpiece in which an abnormality is detected when an abnormality is detected by the comparison unit. .

  A processing apparatus such as a cutting apparatus according to the second aspect of the present invention may have the preliminary processing apparatus described above.

The processing apparatus according to the third aspect of the present invention is:
A processing tool for processing the workpiece;
A drive shaft for driving the processing tool;
A holding member for holding the workpiece;
An X-axis moving mechanism for moving the holding member relative to the processing tool in the X-axis direction;
A Y-axis moving mechanism for moving the drive shaft relative to the workpiece in the Y-axis direction;
A Z-axis moving mechanism for moving the drive shaft relative to the workpiece in the Z-axis direction;
Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
Comparing means for judging whether or not vibration change data obtained from primary data of vibration detected by the vibration detecting means exceeds a threshold value.

  In the processing apparatus according to the third aspect of the present invention, the defect of the processing trace corresponding to the chipping or the like leading to the defect, for example, several tens of μm, is determined by the comparison means whether the vibration change data exceeds the threshold value. Hereinafter, it becomes easy to detect a defect of a processing mark of preferably 10 μm or less from vibration special change data.

  The processing apparatus which concerns on the 3rd viewpoint of this invention may further have an imaging means which images the process trace of the said workpiece | work by the said processing tool.

Moreover, the processing apparatus which concerns on the 3rd viewpoint of this invention is
Threshold value for calculating a threshold value based on vibration change data obtained from primary data of vibration detected by the vibration detection means, and processing trace change data indicating a time change of the processing trace of the workpiece by the imaged processing tool. You may further have a calculation means.

A processing apparatus according to the fourth aspect of the present invention is:
A processing tool for processing the workpiece;
A drive shaft for driving the processing tool;
A holding member for holding the workpiece;
An X-axis moving mechanism for moving the holding member relative to the processing tool in the X-axis direction;
A Y-axis moving mechanism for moving the drive shaft relative to the workpiece in the Y-axis direction;
A Z-axis moving mechanism for moving the drive shaft relative to the workpiece in the Z-axis direction;
Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
A discriminating unit for discriminating data obtained from the vibration detecting unit based on a discriminant criterion obtained from the correlation (collation result) obtained by the collating unit of the preliminary processing apparatus according to any one of the above. .

  In the processing apparatus according to the fourth aspect of the present invention, the data obtained from the vibration detecting means is discriminated based on the discrimination criterion obtained from the correlation (collation result) obtained by the collating means of the preliminary machining apparatus. As a result, it becomes easy to detect a defect in a machining trace corresponding to chipping or the like that leads to a defect, for example, a defect in a machining trace of several tens of μm or less, preferably 10 μm or less, from vibration special change data.

  Preferably, the processing apparatus according to the fourth aspect of the present invention further includes a determination criterion storage unit that stores a determination criterion from the preliminary processing apparatus. From the preliminary processing apparatus, discrimination standard data (including logical expressions, algorithms, programs, etc.) is transmitted directly or via the Internet by wired or wireless communication. Alternatively, the discrimination reference data may be transferred from the preliminary processing device to the storage device of the processing device via a removable storage device.

Preferably, the processing apparatus according to the fourth aspect of the present invention includes:
Vibration change data creating means for creating vibration change data related to secondary data of vibration obtained from primary data of vibration detected by the vibration detecting means;
The discriminating means discriminates special change data from vibration change data obtained by the vibration detecting means and the vibration change data creating means when machining the workpiece by the processing tool, based on the discrimination criterion, The machining state is determined.

  In the machining apparatus according to the fourth aspect of the present invention, it is possible to accurately detect a machining defect of a workpiece by detecting special change data from a plurality of types of vibration change data based on a discrimination criterion found by the preliminary machining apparatus. Can be found at

  Preferably, the processing tool is a cutting tool, and the discriminating means can discriminate the presence or absence of chipping of the workpiece at the cutting position of the workpiece.

  The machining apparatus according to a fourth aspect of the present invention further includes an abnormal position storage unit that stores a machining position of the workpiece in which an abnormality is detected when an abnormality is detected by the determination unit. Based on the data stored in the abnormal position storage means, it can be used for inspection such as identification of the cause of the abnormality.

The machining state detection apparatus according to the first aspect of the present invention is:
Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
Comparison means for determining whether or not vibration change data obtained from the signal detected by the vibration detection means exceeds a threshold,
A signal is output based on the comparison result of the comparison means.

  By attaching the machining state detection apparatus according to the first aspect of the present invention to a general machining apparatus, it is possible to determine whether the vibration change data exceeds a threshold value by using a comparison means, thereby causing chipping that leads to defects. It becomes easy to detect the defect of the machining trace corresponding to the above, for example, the defect of the machining trace of several tens μm or less, preferably 10 μm or less from the vibration special change data.

The machining state detection apparatus according to the second aspect of the present invention is:
Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
A threshold value for calculating a threshold value based on vibration change data obtained from primary data of vibration detected by the vibration detection means and processing trace change data indicating a time change of the processing trace of the workpiece by the imaged processing tool. And calculating means.

  By attaching the machining state detection apparatus according to the second aspect of the present invention to a general machining apparatus, the above-described preliminary machining apparatus according to the present invention can be realized.

The machining state detection apparatus according to the third aspect of the present invention is:
Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
A discriminating unit for discriminating data obtained from the vibration detecting unit based on a discriminant criterion obtained from the correlation (collation result) obtained by the collating unit of the preliminary processing apparatus according to any one of the above. .

  By determining whether or not specific special change data is included in the vibration change data by attaching the processing state detection device according to the third aspect of the present invention to a general processing device, It becomes easy to detect a defect in a processing mark corresponding to chipping or the like that leads to a defect, for example, a defect in a processing mark of several tens of μm or less, preferably 10 μm or less, from vibration special change data.

  Preferably, the machining state detection device according to the third aspect of the present invention further includes a discrimination criterion storage unit that stores the discrimination criteria from the preliminary machining device described above. From the preliminary processing apparatus, discrimination standard data (including logical expressions, algorithms, programs, etc.) is transmitted directly or via the Internet by wired or wireless communication. Alternatively, the discrimination reference data may be transferred from the preliminary processing apparatus to the storage means via a removable storage means.

Preferably, the machining state detection device according to the third aspect of the present invention is:
Vibration change data creating means for creating vibration change data obtained from primary data of vibration detected by the vibration detecting means,
The discriminating means discriminates special change data from vibration change data obtained by the vibration detecting means and the vibration change data creating means when machining the workpiece by the processing tool, based on the discrimination criterion, The machining state is determined.

  In the machining state detection device according to the third aspect of the present invention, machining failure of a workpiece is detected by detecting special change data from a plurality of types of vibration change data based on a discrimination criterion found by a preliminary machining device. Can be found with high accuracy.

The machining state detection method according to the first aspect of the present invention includes:
Imaging a work mark of the workpiece by a processing tool;
Detecting vibration during processing of the workpiece by the processing tool;
Comparing the machining trace change data indicating the time change of the processing trace and the vibration change data indicating the time change of the vibration;
Obtaining machining defect data corresponding to machining defects of the workpiece by the machining tool from the machining trace change data, and extracting special change data of the vibration change data corresponding to the machining defect data.

  According to the machining state detection method according to the first aspect of the present invention, defects in machining traces corresponding to chipping or the like leading to defects, for example, defects in machining traces of several tens μm or less, preferably 10 μm or less, It becomes easy to detect from the change data. That is, according to the special change data obtained by the machining state detection method of the present invention, by comparing the vibration change due to the actual machining of the machining with the special change data, machining defects such as chipping that leads to defects can be detected in real time. It becomes possible to detect with high accuracy.

Preferably, the machining state detection method according to the first aspect of the present invention comprises:
When the vibration change data is equal to or greater than a threshold value, setting a threshold value for the special change data so as to determine that a machining failure of the workpiece by the processing tool has occurred;
And determining whether vibration change data obtained from the signal detected by the vibration detecting means exceeds the threshold value.

  By simply determining whether or not the vibration change data obtained from the signal detected by the vibration detection means exceeds a specific threshold, it is possible to easily detect processing defects such as chipping leading to defects in real time with high accuracy. Is possible.

The machining state detection method according to the second aspect of the present invention includes:
A process of detecting vibrations when machining a workpiece with a machining tool;
Imaging a work trace of the workpiece by the processing tool;
Creating process trace change data related to the position change of the imaged process trace;
Creating vibration change data obtained from the primary data of the detected vibration;
Based on the correlation (matching result) found by comparing the machining trace change data and the vibration change data, the special change data of the vibration change data highly related to the processing failure of the workpiece by the processing tool Extracting and calculating a discrimination criterion for finding a machining defect of the workpiece from the vibration change data.

  By applying the machining state detection method according to the second aspect of the present invention to a general machining apparatus, it is possible to determine whether or not specific special change data is included in the vibration change data. It becomes easy to detect a defect of a processing mark corresponding to connected chipping, for example, a defect of a processing mark of several tens of μm or less, preferably 10 μm or less from the vibration special change data with high accuracy.

  The workpiece machining method of the present invention has the machining state detection method described above.

FIG. 1 is a front view of a cutting apparatus as a processing apparatus according to an embodiment of the present invention. FIG. 2 is a side view of the cutting apparatus shown in FIG. FIG. 3 is a block diagram showing the relationship between the first cutting state detection device and the second cutting state detection device. 4A is a schematic diagram showing an example of cutting mark image data obtained by the camera shown in FIG. 3, and FIG. 4B is obtained by performing signal processing on the cutting mark image data shown in FIG. 4A. FIG. 4C is a time chart showing an example of machining trace change data, FIG. 4C is a time chart showing an example of primary data of vibration detection obtained by the vibration sensor shown in FIG. 3, and FIG. It is a time chart figure of the vibration change data obtained by carrying out signal processing of the primary data of vibration detection shown in FIG. FIG. 5 is a block diagram showing the relationship between the first machining state detection device and the second machining state detection device according to another embodiment of the present invention. FIG. 6A is a schematic diagram showing an example of processing mark image data obtained by the camera shown in FIG. FIG. 6B is a schematic diagram showing another example of processing mark image data obtained by the camera shown in FIG. FIG. 7A is a graph showing a change in the position of the cutting edge along the machining direction, showing an example of machining trace change data obtained by performing signal processing on the machining trace image data shown in FIG. 6A. FIG. 7B is a graph showing a change in the position of the cutting edge along the machining direction, showing an example of machining trace change data obtained by performing signal processing on the machining trace image data shown in FIG. 6B. FIG. 8 is a graph in which data indicating the change in the position of the cutting edge shown in FIG. 7A is obtained over the entire region. FIG. 9 is a graph obtained by adding data indicating the change in position of the cutting edges on both sides shown in FIG. FIG. 10 is an example of the primary data transition of vibration detection obtained by the vibration sensor shown in FIG. 5, and the horizontal axis is a graph showing the machining position. FIG. 11 is a conceptual diagram with the horizontal axis representing the frequency obtained by Fourier transforming the primary data of the vibration shown in FIG. FIG. 12 is a graph of an example for each frequency obtained by Fourier transforming the primary data of the vibration shown in FIG. FIG. 13 is a graph of an example obtained by statistically processing the primary data of the vibration shown in FIG. FIG. 14 is a graph for explaining that window processing is performed on the vibration change data obtained in FIGS. FIG. 15 is a graph for explaining the histogram formation for each data in the range windowed in FIG. FIG. 16 is a graph for explaining that the special change data is extracted using the data histogramd for each window in FIG. FIG. 17 is a diagram for explaining the calculation of a discrimination criterion for finding a machining defect of the workpiece from the vibration change data based on the special change data extracted for each window in FIG. FIG. 18 is a graph showing whether or not there is a processing defect along the processing direction obtained by performing processing by comparing the processing trace change data and the vibration change data.

  Hereinafter, the present invention will be described based on embodiments shown in the drawings.

Cutting device 2 as a processing apparatus according to an embodiment of the present invention shown in the first embodiment Figure 1 and 2, pre-processing apparatus as a master unit is attached first machining state detecting apparatus 2a shown in FIG. 3 The second machining state detection device 2b shown in FIG. 3 is attached and used as at least one of the actual cutting devices as slave units. First, the cutting device 2 will be described with reference to FIGS. 1 and 2.

  The cutting device 2 has a disk-shaped grindstone 4 as a processing tool. The grindstone 4 can be rotated around the Y axis by a spindle 6 as a drive shaft. The spindle 6 is held by a spindle support 8. The support 8 is held so as to be movable in the Z-axis direction by a Z-axis rail 20 as a Z-axis moving mechanism.

  The Z-axis rail 20 is held so as to be movable in the Y-axis direction by a Y-axis rail 22 as a Y-axis moving mechanism. The Y-axis rail 22 is fixed to a support wall 19 fixed on the fixed base 18. Note that the Z-axis rail 20 may be fixed to the Y-axis rail 22 and the support 8 may function as, for example, a Y-axis moving mechanism. The support 8 supports the spindle 6 so as to be movable along the Y-axis. May be.

  On the fixed base 18, an X-axis rail 16 that functions as an X-axis moving mechanism is arranged and fixed along the X-axis direction. A lower table 14 is arranged on the X-axis rail 16 so as to be movable in the X-axis direction. An upper table 12 as a holding member is held on the lower table 14 so as to be rotatable around the Z axis (θ direction). A workpiece 10 is detachably fixed on the upper table 12.

  In order to detachably hold the workpiece 10 on the upper table 12, a plurality of vacuum suction holes are formed on the upper surface of the upper table 12, and the workpiece 10 can be sucked and held on the upper table 12. It has become. The work 10 may be detachably held on the upper table 12 by other means. In this embodiment, the X axis, the Y axis, and the Z axis are perpendicular to each other, the Y axis substantially coincides with the rotation axis of the grindstone 4 (rotation axis of the spindle 6), and the Z axis substantially coincides with the vertical direction. To do.

  In the present embodiment, since the lower table 14 is held by the X-axis rail 16 so as to be movable in the X-axis direction, the upper table 12 as a holding member mounted on the lower table 14 is used as a processing tool. The whetstone 4 is held so as to be relatively movable in the X-axis direction. Further, since the Z-axis rail 20 is held on the Y-axis rail 22 so as to be movable in the Y-axis direction, the spindle 6 and the grindstone 4 can be moved relative to the workpiece 10 in the Y-axis direction. In addition, since the spindle support 8 is held so as to be movable in the Z-axis direction with respect to the Z-axis rail 20, the spindle 6 and the grindstone 4 can be moved relative to the workpiece 10 in the Z-axis direction. Yes.

  The disc 6 is rotated around the Y axis by the spindle 6. The rotating grindstone 4 comes into contact with the surface of the workpiece 10 by moving the support 8 along the Z-axis rail 20 downward in the Z-axis. By moving the lower table 14 along with the upper table 12 along the X-axis rail 16 in the X-axis direction, the workpiece 10 is cut and cut along the X-axis direction by the rotating grindstone 4.

  Note that a sheet (not shown) or the like exists between the workpiece 10 and the upper table 12 so that the grindstone 4 does not touch the upper table 12, and the grindstone 4 moves in the Z direction so as to cut halfway through the sheet or the like. To do.

  As shown in FIG. 3, the first machining state detection device 2a according to the present embodiment is attached to, for example, the cutting device 2 shown in FIGS. 1 and 2, and includes a camera 30 as an imaging unit and vibration as a vibration detection unit. Sensor 40. For example, as shown in FIG. 1, the camera 30 is attached to the spindle support 8 so that the rotating grindstone 4 can capture a cutting trace as a machining trace for cutting the workpiece 10 or in real time if possible. It has become. The primary data 32 of the cutting trace is shown in FIG. Note that the primary data 32 is captured image data itself obtained by the camera 30.

  The vibration sensor 40 shown in FIG. 3 is attached to the upper table 12 to which the workpiece 10 is detachably fixed, for example, as shown in FIGS. 1 and 2, and the vibration when the rotating grindstone 4 cuts the workpiece 10. It can be detected in real time. The primary data 42 of vibration detected by the vibration sensor 40 is shown in FIG. The primary data 42 is data indicating a change over time of the detection signal itself obtained by the vibration sensor 40.

  In the present embodiment, the vibration sensor 40 may be any sensor that can detect any vibration, and is not particularly limited. A displacement sensor, a speed sensor, an acceleration sensor, an acoustic sensor, and a surface acoustic wave sensor (AE sensor as an example). Etc. are also included. The camera 30 is not particularly limited as long as it can capture a processing mark such as a cutting mark.

  As shown in FIG. 3, the first machining state detection device 2 a of the present embodiment includes a cutting trace change data creation unit 33. The cutting trace change data creation means 33 generates cutting trace change data 34 related to the temporal change of the cutting trace shown in FIG. 4B from the primary data 32 of the cutting trace shown in FIG. produce. The cutting mark change data 34 is a graph showing the change in the cutting width substantially perpendicular to the cutting direction on the vertical axis and showing with time. The processing defect data 34a appears at a portion where the cutting width has changed greatly. A typical example of the processing defect data 34a is processing defects such as chipping of a cutting portion of the workpiece 10 by the grindstone 4 as a processing tool.

  As shown in FIG. 3, the first machining state detection device 2 a of this embodiment includes vibration change data creation means 43. The vibration change data creation means 43 creates vibration change data 44 related to the time change of vibration shown in FIG. 4D from the primary data 42 of vibration shown in FIG. 4C detected by the vibration sensor 40.

  The vibration change data 44 is a graph obtained by subjecting the primary data 42 of vibration to specific signal processing, and the magnitude of the signal is plotted on the vertical axis and shown over time. As shown in FIG. 4D, the present inventors have found that the special change data 44a appears corresponding to the processing defect data 34a shown in FIG. 4B.

  As shown in FIG. 3, the first machining state detection device 2 a according to the present embodiment includes a matching unit 50. The verification unit 50 compares the cutting trace change data 34 related to the time change of the cutting trace shown in FIG. 4B and the vibration change data 44 related to the time change of the vibration. Specifically, the change start time t1 and the change end time t2 of the cutting trace change data 34 are made to correspond to the time axis (horizontal axis) of the vibration change data. Further, the first machining state detection device 2a of the present embodiment further includes an extraction unit 52, a threshold value determination unit 54, and a storage unit 56.

  In the extracting means 52, the vibration change data shown in FIG. 4D corresponding to the processing defect data 34a shown in FIG. 4B based on the change start time t1 and change end time t2 obtained by the collating means 50. 44 special change data 44a are extracted. That is, the special change data 44a is extracted based on the correlation between FIG. 4B and FIG.

  3 determines the threshold value 46 which is the minimum value of the special change data 44a of the vibration change data 44 shown in FIG. 4D extracted by the extraction means 52. The threshold value determination means 54 shown in FIG. When the vibration change data 44 shown in FIG. 4D is equal to or greater than the threshold value 46, the threshold value 46 has a processing failure such as chipping of the workpiece 10 by the grindstone 4 (processing failure to the extent that the product becomes defective). It is decided so that it can be judged. 4A to 4D, the horizontal axis indicates the elapsed time from the start of machining, but the elapsed time corresponds to the cutting position in the cutting direction which is the machining direction.

  In the storage unit 56, the threshold data determined by the threshold determination unit 54 is stored. The threshold data stored in the storage means 56 is also stored in the storage means 56a of the plurality (or singular) of the second machining state detection devices 2b shown in FIG. The storage unit 56a and the storage unit 56 may be the same or different. For example, if the first machining state detection device 2a of the present embodiment is attached to the cutting device 2 shown in FIGS. 1 and 2, the cutting device 2 becomes a cutting preliminary device as a master unit, and the second machining state detection device 2b is used. If attached to the cutting device 2 shown in FIGS. 1 and 2, the cutting device 2 becomes a cutting device as a slave unit. When the parent machine cutting device 2 and the child machine cutting device 2 are the same, the storage means 56 and the storage means 56a are configured in the same way.

  When the cutting device 2 to which the first machining state detection device 2a is attached is different from the cutting device 2 to which the second machining state detection device 2b is attached, the storage unit 56 and the storage unit 56a are connected to each other by wireless or wired communication. The data of the threshold value 46 (see FIG. 4D) updated by the storage means 56 and updated by the storage means 56 may be simultaneously updated by the storage means 56a. Further, a network server (not shown) may be prepared between the storage unit 56 and the storage unit 56a, and the threshold value 46 updated by the storage unit 56 may be updated as necessary by the storage unit 56a. Alternatively, the threshold data stored in the storage unit 56 may be moved to the storage unit 56a using a transportable storage medium to update the data. By updating the threshold data, it becomes possible to more accurately detect machining abnormality such as cutting abnormality.

  The storage means 56 and 56a are not particularly limited, and examples thereof include a hard disk, a semiconductor memory, a recording disk, and a recording tape attached to a computer (including a personal computer).

  In the first machining state detection device 2a shown in FIG. 3, the cutting trace change data creation means 33, vibration change data creation means 43, collation means 50, extraction means 52, and threshold value determination means 54 are the same as those shown in FIGS. It may be configured by a dedicated circuit that constitutes a part of the control device of the device 2 or may be configured by a program of an individual computer. Further, the cutting trace change data creating unit 33 and the vibration change data creating unit 43 may be included in the collating unit 50 or the extracting unit 52, and the collating unit 50 may be included in the extracting unit 52. Further, the threshold value determining means 54 may be included in the collating means 50 or the extracting means 52.

  A second machining state detection device 2b shown in FIG. 3 is attached to the cutting device 2 shown in FIGS. 1 and 2, for example, and has a vibration sensor 40 as vibration detection means. Unlike the first machining state detection device 2a shown in FIG. 3, the camera 30 is not necessarily provided, but may be provided. In any case, the second processing state detection device 2b does not need the image data 32 of the processing marks described above.

  The vibration sensor 40 of the second machining state detection device 2b shown in FIG. 3 is the same as the vibration sensor 40 of the first machining state detection device 2a, but does not necessarily have to be exactly the same. As shown in FIGS. 1 and 2, for example, the vibration sensor 40 is attached to the upper table 12 to which the workpiece 10 is detachably fixed, and can detect vibrations when the rotating grindstone 4 cuts the workpiece 10 in real time. It has become. The primary data 42 of vibration detected by the vibration sensor 40 is shown in FIG.

  The second machining state detection device 2 b includes vibration change data creation means 43. The vibration change data creation means 43 has the same configuration as the vibration change data creation means 43 of the first machining state detection device 2a, and the primary data 42 of vibration shown in FIG. 4C detected by the vibration sensor 40. The vibration change data 44 relating to the time change of vibration shown in FIG.

  As shown in FIG. 3, the second machining state detection device 2 b of this embodiment further includes a comparison unit 60. The comparing means 60 uses the threshold data 46 (see FIG. 4D) in which the vibration change data obtained by the vibration change data creating means 43 using the primary data detected by the vibration sensor 40 is stored in the storage means 56a. ) Or not. As shown in FIG. 4D, when the comparison means 60 includes the special change data 44a in the vibration change data 44 and the output signal of the data 44a exceeds the threshold value 46, the warning means 62 is provided. Start up.

  The warning means 62 outputs a warning signal such as an alarm for notifying that a machining abnormality such as chipping has occurred at the cutting location of the workpiece 10 shown in FIGS. 1 and 2, for example. The warning signal may be a signal that emits a warning sound or a signal that displays a warning image. The warning image is displayed on the display device screen of the control device of the second machining state detection device 2b, for example.

  In the warning means 62, when an abnormality (machining abnormality such as chipping) is detected by the comparison means 60, the machining position of the workpiece 10 where the abnormality is detected may be stored in the storage means 56a. In the second machining state detection device 2b, the vibration change data creation means 43, the comparison means 60, and the warning means 62 are configured by a dedicated circuit that constitutes a part of the control device of the cutting device 2 shown in FIGS. However, it may be configured by a program of a computer serving as the control device.

  In the first machining state detection device 2a according to the present embodiment, the cutting trace of the workpiece 10 by the grindstone 4 can be imaged using the camera 30 as the imaging means. In addition, in order to image a cutting trace on-line at the time of the cutting process by the grindstone 4, the imaging may be performed while removing a processing liquid such as a cutting fluid or a polishing liquid so that the cutting trace can be easily captured by the camera 30. .

  In the first machining state detection device 2a of the present embodiment, for example, the cutting trace change data means 33 shown in FIG. Cutting mark change data 34 can be created. In addition, the vibration sensor 40 can detect vibration during cutting of the workpiece 10 by the grindstone 4. Furthermore, vibration change data 44 related to the time change of vibration can be created from the data detected by the vibration sensor 40.

  In the collating means 50 shown in FIG. 3, the correlation between them can be obtained by comparing the cutting mark change data 34 shown in FIG. 4 (B) with the vibration change data 44 shown in FIG. 4 (D). . In the machining state detection apparatus of this embodiment, by correlating the change data of cutting traces such as chipping that leads to product defects with the change data of vibrations, the vibration change data can be used to cope with chipping that leads to defects. It becomes possible to judge the defect of the cutting trace.

  In the first machining state detection device 2a and the detection method of the present embodiment, a defect in the cutting trace corresponding to chipping or the like that leads to a defect, for example, a defect in the cutting trace of several tens μm or less, preferably 10 μm or less is shown in FIG. ) Can be detected from the vibration change data 44 shown in FIG. In the past, it was possible to detect machining defects such as chipping of about 100 μm by using the detection signal of the vibration detection sensor. However, the vibration detection signal was used to detect cutting defects of several tens of μm or less, preferably 10 μm or less. It was difficult to detect from (for example, the signal shown in FIG. 4C).

  Correlation data between vibration change data and machining defects obtained by the first machining state detection device 2a of the present embodiment and the method using the same is stored in the storage unit 56 as threshold data. Threshold value data stored in the storage means 56 is stored in the storage means 56a and used in the cutting apparatus 2 as an actual processing apparatus, so that processing defects such as chipping leading to defects can be accurately detected in real time. Is possible.

  According to the machining state detection device 2b according to the present embodiment, chipping that leads to a defect is made by comparing the vibration change due to actual cutting with the special change data 44a obtained by the first machining state detection device 2a. It is possible to detect machining defects such as in real time with high accuracy. That is, it is possible to easily detect a processing defect such as chipping that leads to a defect with high accuracy in real time only by determining whether or not the vibration change data obtained from the signal detected by the vibration sensor 40 exceeds a specific threshold value. It becomes possible to do.

Second Embodiment A cutting apparatus as a processing apparatus according to a second embodiment of the present invention is basically the same as the cutting apparatus 2 according to the first embodiment shown in FIGS. 1 and 2. The cutting device according to the second embodiment has a first processing state detection device 2c shown in FIG. 5 attached thereto and becomes a preliminary processing device as a master machine, or a second processing state detection device 2d shown in FIG. 5 attached. It is used as at least one of the actual cutting devices as slave units. Hereinafter, the description of the same part as the description of the first embodiment will be omitted as much as possible, and the configuration and operation effect unique to the second embodiment will be described in detail.

  As shown in FIG. 5, the first machining state detection device 2c of the present embodiment includes machining mark change data creation means 33a. From the image data of the machining trace which is the primary data of the image shown in FIG. 6A captured by the camera 30, first, the machining trace change data creating means 33 a is arranged on both sides along the position in the cutting direction as shown in FIG. 7A. Create data for the predetermined position of the cutting edge. Similarly, the processing trace image data shown in FIG. 6B captured by the camera 30 can also generate data on other positions of the cutting edges on both sides along the position in the cutting direction, as shown in FIG. 7B.

  The machining trace change data creating means 33a shown in FIG. 5 connects the digitized data shown in FIG. 7A and the digitized data shown in FIG. 7B, so that all the cutting edges on both sides along the position in the cutting direction as shown in FIG. It is also possible to create secondary image data for the region. The direction perpendicular to the chipping cutting direction of the secondary data of the image in FIG. 8 (the direction of the vertical axis) is shown with the magnification emphasized.

  Further, the machining mark change data creation means 33a shown in FIG. 5 creates secondary data of the image based on the data shown in FIG. 8 and adds data related to chipping of the cutting edges on both sides as shown in FIG. Also good.

  As shown in FIG. 5, the first machining state detection device 2 c of the present embodiment includes a vibration sensor 40 configured by an AE sensor or the like. The primary data of the vibration shown in FIG. 10 detected by the vibration sensor 40 constituted by an AE sensor or the like is data corresponding to the image data of the cutting trace shown in FIG. 8 or FIG. It is the primary data obtained from the AE sensor when the cutting process shown is performed. Even if only the primary data detected by the AE sensor shown in FIG. 10 is analyzed, it is difficult to determine whether there are many or few processing defects such as chipping.

  In the present embodiment, the vibration change data creation means 43a shown in FIG. 5 is, for example, secondary data of vibration from the primary data of vibration shown in FIG. 10 detected by the vibration sensor 40 configured by an AE sensor or the like. You may have the data conversion means which produces the vibration change data data-converted for every frequency shown in FIG. This data conversion means is also a statistical processing means. From the primary data of vibration shown in FIG. 10, for example, as shown in FIG. 13, the average value of vibration data at each processing position is plotted along the position in the processing direction. Vibration change data, vibration change data indicating the length from the minimum peak to the maximum peak of vibration data at each machining position are generated. Other statistical processing data includes vibration change data in which the maximum value of vibration data at each machining position is plotted along the position in the machining direction, and the minimum value of vibration data at each machining position along the position in the machining direction. The plotted vibration change data, vibration change data in which the variation σ of vibration data at each machining position is plotted along the position in the machining direction, and the like are exemplified.

  In the data conversion means of the vibration change data creation means 43a, when Fourier transform is performed based on the primary data of vibration shown in FIG. 10, the secondary data of vibration is m times the predetermined reference frequency (f) as shown in FIG. A peak of vibration change data occurs for each frequency (m is a natural number), and a valley of vibration change data occurs every (m + 0.5) times (m is a natural number) a predetermined reference frequency (f). In this embodiment, the predetermined reference frequency can be defined as a frequency related to the movement of the processing tool, for example, and is a vibration frequency based on the rotational speed of the grindstone 4 as the processing tool shown in FIGS. 1 and 2. Or the vibration frequency etc. based on the rotation speed of the X direction movement motor of the lower table 14 are illustrated.

  As an example, when the rotation speed of the spindle 6 that rotates the processing tool of FIG. 1 is 30000 rpm, the vibration frequency of the spindle 6 is 500 Hz, and this is set as a reference frequency, for example, 24500 Hz every 0 to 500 Hz as shown in FIG. Up to 50 data can be obtained for each frequency.

  Furthermore, in the present embodiment, the vibration change data creation unit 43a shown in FIG. 5 may include a filtering unit that enhances a signal. For example, the filtering means performs data conversion every m times the reference frequency (f) shown in FIG. 11 obtained from the primary data of the vibration shown in FIG. The peak of the vibration change data is filtered with a predetermined bandwidth (for example, ± 125 Hz) to obtain a signal (S). Similarly, the filtering means performs a filtering process with a predetermined bandwidth (for example, ± 125 Hz) on the valley of the vibration change data that has been data-converted every (m + 0.5) times of the reference frequency (f), thereby generating noise (N ). As the secondary data of the vibration, for example, the vibration change data obtained by obtaining the ratio (S / N) of the signal (S) with the noise (N), or the signal (SN) obtained by subtracting the noise (N) from the signal (S) The vibration change data etc. for which

Further, in the present embodiment, the vibration change data creating unit 43a shown in FIG. 5 performs n windows W _{1 to} W in a predetermined range as shown in FIG. 14 with respect to the vibration change data shown in FIGS. You may have the window means which performs a data process for every _n . The horizontal axis width of the window is not particularly limited, but corresponds to a predetermined length along the machining direction or a unit of machining time from the machining start time.

The window means may overlap adjacent windows W _{1 to} W _n and perform data processing such as histogram processing for each window as shown in FIG. 15 for the vibration change data. The overlap ratio is preferably 50% or more, and more preferably 80% or more, along the horizontal axis (position in the processing progress direction).

  In FIG. 15, multiple types of vibration change data shown in FIG. 14 may be subjected to overlapping window processing to create histogram data respectively.

  As shown in FIG. 5, the first machining state detection device 2 c of the present embodiment includes a matching unit 50 a and a calculation unit 53. The verification unit 50a and the calculation unit 53 may have different functions, but may be integrated. In the collating means 50a, for example, the vibration change data shown in FIG. 14 or FIG. 15 and the machining trace change data related to the positional change of the machining trace shown in FIG. 8 or FIG. A relationship (matching result) can be obtained.

  The computing means 53 has machine learning means. The machine learning means, for example, compares and compares the machining mark change data shown in FIG. 8 or FIG. 9 with the vibration change data shown in FIGS. 12 to 13, thereby satisfying a plurality of types of vibration change data conditions shown in FIG. Machine learning is performed to find special change data (data circled in FIG. 16) from the corresponding histogram data. Examples of the algorithm of the machine learning means include random forest or deep learning.

  For example, the calculation means 53 may select special change data (the ellipse shown in FIG. 16) that is generated in common at the chipping timing from the histogram data shown in FIG. 15 corresponding to the machining position where the chipping occurs as shown in FIG. 8 or FIG. Machine learning to find the data enclosed in By performing the machine learning, the calculation means 53 detects “special change data (data surrounded by an ellipse shown in FIG. 16) of any vibration change data, thereby detecting the machining failure of the workpiece. A discrimination criterion such as “whether or not the presence / absence can be found with high accuracy” is calculated. An example of the discrimination criterion is shown in a part of the logical expression program shown in FIG.

  Further, the calculation means 53 shown in FIG. 5 creates the abnormal change data 63 shown in FIG. 18 based on the machining mark change data shown in FIGS. 8 and 9 and the vibration change data shown in FIGS. The abnormal change data 63 shown in FIG. 18 is a graph in which the position in the cutting direction (processing direction) (corresponding to the time from the start of processing) is set on the horizontal axis, and at this position, it is determined whether there is a processing defect such as chipping. It can also be shown in the form of In the abnormal change data 63 shown in FIG. 18, for example, the numeral 0 on the horizontal axis indicates, for example, a machining start (cutting start) position, and the numeral 100 on the horizontal axis indicates, for example, a machining end (cutting end) position. . The number 1 on the vertical axis indicates that there is a processing abnormality such as chipping of 10 μm or more at the processing position on the horizontal axis, and the number 0 indicates that the processing position on the horizontal axis is, for example, 10 μm or more. This indicates that there is no processing abnormality such as chipping.

  In FIG. 17, for example, the presence or absence of chipping is based on the discrimination criteria based on the special change data (the data surrounded by circles shown in FIG. 16) found by the computing means 53 shown in FIG. 5 at the timing when the chipping shown in FIG. 18 occurs. An example of a logical expression for predicting is disclosed. This logical formula program is stored in the discrimination reference storage means 56c shown in FIG.

  The first machining state detection device 2c shown in FIG. 5 has output means (not shown), and the discrimination reference data (including the program / the same applies hereinafter) stored in the discrimination reference storage means 56c, for example, communication means Is output to the discrimination reference storage means 56d of the second machining state detection device 2d. The discrimination reference storage unit 56c and the discrimination reference storage unit 56d may be storage units different from each other, or may be a single storage unit.

  If the 1st processing state detection apparatus 2c of this embodiment is attached to the cutting apparatus 2 shown in FIG. 1 and FIG. 2, the cutting apparatus 2 will become the cutting preliminary apparatus (preliminary processing apparatus) as a main | base station, and will be 2nd processing state. If the detection device 2d is attached to the cutting device 2 shown in FIGS. 1 and 2, the cutting device 2 becomes a cutting device (processing device) as a slave. When the parent machine cutting device 2 and the child machine cutting device 2 are the same, the storage means 56c and the storage means 56d are configured in the same way.

  When the cutting device 2 to which the first machining state detection device 2c is attached is different from the cutting device 2 to which the second machining state detection device 2d is attached, the storage unit 56c and the storage unit 56d are connected by wireless or wired communication. The data of the discrimination criteria (see FIG. 17) updated by the storage means 56c may be updated simultaneously by the storage means 56d. Further, a network server (not shown) may be prepared between the storage unit 56c and the storage unit 56d, and the determination criteria updated in the storage unit 56c may be updated as necessary in the storage unit 56d. Alternatively, the determination criterion stored in the storage unit 56c may be moved to the storage unit 56d using a transportable storage medium to update the data. By updating the discrimination standard, it becomes possible to detect a machining abnormality such as a cutting abnormality more accurately.

  The storage means 56c and 56d are not particularly limited, and examples thereof include a hard disk, a semiconductor memory, a recording disk, and a recording tape attached to a computer (including a personal computer).

  In the first machining state detection device 2c shown in FIG. 5, the machining mark change data creation means 33a, the vibration change data creation means 43a, the collation means 50a, and the calculation means 53 are the control device of the cutting device 2 shown in FIGS. However, it can also be configured by a computer program serving as the control device. Further, the machining mark change data creation unit 33 a and the vibration change data creation unit 43 a may be included in the collation unit 50 a or the calculation unit 53, and the collation unit 50 a may be included in the calculation unit 53. In addition, a determination unit 61 and / or a chipping detection unit 62a described later may be included in the collation unit 50a or the calculation unit 53.

  The second machining state detection device 2d shown in FIG. 5 is attached to the cutting device 2 shown in FIGS. 1 and 2, for example, and has a vibration sensor 40 as vibration detection means. Unlike the first machining state detection device 2c, the second machining state detection device 2d shown in FIG. 5 does not necessarily include the camera 30, but may include it. In any case, the second machining state detection device 2d does not need data relating to the actual machining marks shown in FIGS. 6A to 9 described above.

  The vibration sensor 40 of the second machining state detection device 2d shown in FIG. 5 is the same as the vibration sensor 40 of the first machining state detection device 2c, but does not necessarily have to be exactly the same. As shown in FIGS. 1 and 2, for example, the vibration sensor 40 is attached to the upper table 12 to which the workpiece 10 is detachably fixed, and can detect vibrations when the rotating grindstone 4 cuts the workpiece 10 in real time. It has become. For example, primary data of vibration detected by a vibration sensor 40 such as an AE sensor is shown in FIG.

  The second machining state detection device 2d includes vibration change data creation means 43a. The vibration change data creation means 43a has the same configuration as the vibration change data creation means 43a of the first machining state detection device 2c, and the primary data of vibration shown in FIG. 10 detected by the vibration sensor 40 is shown in FIG. Produces vibration change data consisting of histograms related to the secondary vibration data shown.

  As shown in FIG. 5, the second machining state detection device 2 d of this embodiment further includes a determination unit 61. The discriminating means 61 discriminates that the vibration change data (for example, the histogram shown in FIG. 15) obtained by the vibration change data creating means 43a using the primary data detected by the vibration sensor 40 is stored in the storage means 56d. It is determined whether or not a reference logical expression (for example, shown in FIG. 17) is met. When the determination unit 61 determines that special change data (for example, an ellipse portion) is included in vibration change data such as a histogram shown in FIG. 16, for example, the chipping detection unit 62a is activated.

  The chipping detection means 62a outputs a warning signal such as an alarm notifying that a machining abnormality such as chipping has occurred at the cutting location of the workpiece 10 shown in FIGS. The warning signal may be a signal that emits a warning sound or a signal that displays a warning image. The warning image is displayed, for example, on the display device screen of the control device of the second machining state detection device 2d shown in FIG.

  In the chipping detection means 62a, when an abnormality (machining abnormality such as chipping) is detected by the discrimination means 61, the machining position of the workpiece 10 where the abnormality is detected is stored in an abnormal position storage means different from the storage means 56d. It may be memorized. Alternatively, the storage unit 56d may also serve as the abnormal position storage unit. In the second machining state detection device 2d, the vibration change data creation means 43a, the discrimination means 61, and the chipping detection means 62a are configured by a dedicated circuit that constitutes a part of the control device of the cutting device 2 shown in FIGS. However, it may be configured by a computer program serving as the control device.

  In the cutting device and the detection method incorporating the first machining state detection device 2c of the present embodiment, as in the first embodiment, the change data of machining traces such as chipping leading to defects and the vibration change data are associated with each other. On the contrary, it is possible to determine the defect of the machining trace corresponding to chipping or the like leading to the defect from the vibration change data. For example, in the present embodiment, a determination criterion that makes it possible to detect a defect in a processing mark corresponding to chipping that leads to a defect, for example, a defect in a processing mark of several tens of μm or less, preferably 10 μm or less, from vibration change data. Can be found.

  Correlation data between vibration change data and machining defects obtained by a cutting apparatus incorporating the first machining state detection device 2c of the present embodiment and a method using the same is stored in the storage unit 56c as a discrimination criterion. The discrimination criteria stored in the storage means 56c are stored in the storage means 56d, and the second machining state detection device 2d is used in the actual cutting device 2 to accurately detect machining defects such as chipping that lead to defects in real time. It becomes possible to detect well.

  According to the machining state detection device 2d according to the present embodiment, the vibration change data obtained from the primary data of vibration obtained by actual cutting is related to the special change data obtained by the first machining state detection device 2c. By making the determination based on the determination criterion, it is possible to accurately detect a processing defect such as chipping that leads to a defect in real time. That is, it is possible to accurately detect a processing defect such as chipping that leads to a defect in real time with only vibration change data obtained from the signal detected by the vibration sensor 40.

  In the above-described embodiment, data conversion processing such as frequency processing, statistical processing, and noise processing is performed from the primary vibration data to generate secondary vibration data, and window processing is performed on the secondary vibration data. However, it is not limited to this. For example, window processing may be performed on the primary data of vibration, and thereafter data conversion processing such as frequency processing, statistical processing, and noise processing may be performed, and then histogram processing may be performed.

  Further, in the present embodiment, the same processing state detection device 2d as the discriminating means 61 and the chipping detection means 62a of the processing state detection device 2d attached to the cutting device of the slave shown in FIG. You may attach to 2c. In that case, it is also possible to detect machining defects such as chipping in real time from only the detection data detected by the vibration sensor 40 even in the cutting device as the master unit.

  Furthermore, in the above-described embodiment, as the secondary data of vibration obtained from the primary data of vibration, data converted for each frequency, data subjected to statistical processing, data subjected to noise processing, and the like are used. However, the present invention is not limited thereto. Not. For example, vibration change data that has passed through a filter such as a low-pass filter can be exemplified as other secondary data of vibration.

  The present invention is not limited to the above-described embodiment, and can be variously modified within the scope of the present invention.

  For example, the processing device of the present invention is not limited to a cutting device such as a dicer, and can be applied to precision processing devices such as a slicer and a grinder. Further, the workpiece 10 is not limited to a semiconductor wafer, and a circuit board, a green sheet laminate, a glass substrate, and the like are also exemplified.

  Further, the X-axis movement mechanism, the Y-axis movement mechanism, and the Z-axis movement mechanism are not limited to the above-described embodiments. For example, as the X-axis moving mechanism, any mechanism may be used as long as the upper table 12 as the holding member is moved relative to the grindstone 4 as the processing tool in the X-axis direction. For example, a mechanism that moves the grindstone 4 in the X-axis direction with respect to the upper table 12 may be used.

  The Y-axis moving mechanism may be any mechanism as long as it moves the spindle 6 (the grindstone 4 as a processing tool) as a drive shaft relative to the workpiece 10 in the Y-axis direction. . For example, a mechanism for moving the upper table 12 holding the workpiece 10 with respect to the spindle 6 in the Y-axis direction may be used. Further, the Z-axis moving mechanism may be any mechanism as long as it moves the spindle 6 (the grindstone 4 as a processing tool) as a drive shaft relative to the workpiece 10 in the Z-axis direction. . For example, a mechanism for moving the upper table 12 holding the workpiece 10 in the Z-axis direction with respect to the spindle 6 may be used.

2 ... Cutting device (processing device / preliminary processing device)
2a, 2c ... 1st processing state detection device 2b, 2d ... 2nd processing state detection device 4 ... Disk-shaped grindstone (processing tool)
6 ... Spindle (drive shaft)
8 ... Spindle support 10 ... Work piece 12 ... Upper table (holding member)
14 ... Lower table 16 ... X-axis rail (X-axis moving mechanism)
18 ... Fixed base 20 ... Z-axis rail (Z-axis moving mechanism)
22 ... Y-axis rail (Y-axis moving mechanism)
30 ... Camera (imaging means)
32 ... Cutting trace primary data 33 ... Cutting trace change data creation means 33a ... Machining trace change data creation means 34 ... Cutting trace change data 34a ... Defect data 40 ... Vibration sensor (vibration detection means)
42 ... Primary data of vibration 43, 43a ... Vibration change data creation means 44 ... Vibration change data 44a ... Special change data 46 ... Threshold value 50, 50a ... Verification means 52 ... Extraction means 53 ... Calculation means 54 ... Threshold value determination means 56 ... Memory Means 56a, 56c, 56d ... Storage means 60 ... Comparison means 61 ... Discrimination means 62 ... Warning means 62a ... Chipping detection means 63 ... Abnormal change data

Claims (34)

A processing tool for processing the workpiece;
A drive shaft for driving the processing tool;
A holding member for holding the workpiece;
An X-axis moving mechanism for moving the holding member relative to the processing tool in the X-axis direction;
A Y-axis moving mechanism for moving the drive shaft relative to the workpiece in the Y-axis direction;
A Z-axis moving mechanism for moving the drive shaft relative to the workpiece in the Z-axis direction;
Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
A preliminary processing apparatus having It further has an imaging means for imaging the work trace of the work by the processing tool,
The collating means for comparing the machining trace change data related to the time change of the machining trace imaged by the imaging means and the vibration change data related to the time change of the vibration detected by the vibration detection means. The preliminary processing apparatus according to 1.   Based on the correlation obtained by the collating means, from the machining trace change data, machining defect data corresponding to the machining defect of the workpiece by the machining tool is obtained, and the vibration change data corresponding to the machining defect data is specially obtained. The preliminary processing apparatus according to claim 2, further comprising extraction means for extracting change data.   When the vibration change data is equal to or greater than a threshold value, a threshold value determination unit that sets a threshold value for the special change data obtained by the extraction unit so that it is determined that a machining failure of the workpiece by the processing tool has occurred. The preliminary processing apparatus according to claim 3, further comprising:   The preliminary processing apparatus according to claim 4, further comprising storage means for storing the threshold value determined by the threshold value determination means. A processing tool for processing the workpiece;
A drive shaft for driving the processing tool;
A holding member for holding the workpiece;
An X-axis moving mechanism for moving the holding member relative to the processing tool in the X-axis direction;
A Y-axis moving mechanism for moving the drive shaft relative to the workpiece in the Y-axis direction;
A Z-axis moving mechanism for moving the drive shaft relative to the workpiece in the Z-axis direction;
Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
6. A processing apparatus comprising: a comparison unit that compares vibration change data obtained from the signal detected by the vibration detection unit with data obtained by the preliminary processing apparatus according to claim 1.   The processing according to claim 6, wherein the processing tool is a cutting tool so that the workpiece can be cut, and the comparison unit can detect the presence or absence of chipping of the workpiece at a cutting position of the workpiece. apparatus.   8. The processing apparatus according to claim 6, further comprising warning means for outputting an alarm when an abnormality is detected by the comparison means.   The machining apparatus according to any one of claims 6 to 8, further comprising a storage unit that stores a machining position of the workpiece in which an abnormality is detected when an abnormality is detected by the comparison unit. A processing tool for processing the workpiece;
A drive shaft for driving the processing tool;
A holding member for holding the workpiece;
An X-axis moving mechanism for moving the holding member relative to the processing tool in the X-axis direction;
A Y-axis moving mechanism for moving the drive shaft relative to the workpiece in the Y-axis direction;
A Z-axis moving mechanism for moving the drive shaft relative to the workpiece in the Z-axis direction;
Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
A processing device comprising: comparing means for judging whether or not vibration change data obtained from primary data of vibration detected by the vibration detecting means exceeds a threshold value.   The processing apparatus according to claim 10, further comprising an imaging unit that images a processing mark of the workpiece by the processing tool.   A threshold value for calculating a threshold value based on vibration change data obtained from primary data of vibration detected by the vibration detection means and processing trace change data indicating a time change of the processing trace of the workpiece by the imaged processing tool. The processing apparatus according to claim 11, further comprising a calculation unit. Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
Comparison means for determining whether vibration change data obtained from primary data of vibration detected by the vibration detection means exceeds a threshold value,
A machining state detection apparatus that outputs a signal based on a comparison result of the comparison means. Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
Threshold value for calculating a threshold value based on vibration change data obtained from primary data of vibration detected by the vibration detection means, and processing trace change data indicating a time change of the processing trace of the workpiece by the imaged processing tool. A machining state detection device having calculation means. A processing tool for processing the workpiece;
A drive shaft for driving the processing tool;
A holding member for holding the workpiece;
An X-axis moving mechanism for moving the holding member relative to the processing tool in the X-axis direction;
A Y-axis moving mechanism for moving the drive shaft relative to the workpiece in the Y-axis direction;
A Z-axis moving mechanism for moving the drive shaft relative to the workpiece in the Z-axis direction;
Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
An imaging means for imaging the workpiece trace of the workpiece by the processing tool;
Machining trace change data creating means for creating machining trace change data related to the position change of the machining trace imaged by the imaging means;
Vibration change data creating means for creating vibration change data obtained from primary data of vibration detected by the vibration detecting means;
A preparatory machining apparatus having collation means for collating the machining trace change data and the vibration change data.   Based on the collation result obtained by the collating means, the special change data of the vibration change data that is highly related to the machining defect of the workpiece by the processing tool is extracted, and the machining defect of the workpiece is determined from the vibration change data. The preliminary processing apparatus according to claim 15, further comprising calculation means for calculating a discrimination criterion to be found.   The preliminary processing apparatus according to claim 16, further comprising: a discrimination criterion storage unit that stores the discrimination criterion calculated by the calculation unit; and an output unit that outputs the discrimination criterion stored in the discrimination criterion storage unit.   The preliminary processing apparatus according to claim 15, wherein the vibration change data creation means includes data conversion means for performing Fourier transform on primary data of the vibration.   The vibration change data creation means performs Fourier transform on the primary data of the vibration, and uses the vibration change data at a frequency of m times a predetermined reference frequency (f) (m is an absolute value of an integer) as secondary data of vibration. The preliminary processing apparatus according to claim 15, further comprising data conversion means for acquiring.   In addition to the frequency of m times the predetermined reference frequency (f) (m is an absolute value of an integer), the data conversion means is (m + 0.5) times (m is an integer) of the predetermined reference frequency (f). The preliminary processing apparatus according to claim 19, wherein the vibration change data at a frequency of (absolute value) is acquired as secondary data of vibration.   The preliminary processing apparatus according to claim 19 or 20, wherein the reference frequency is a frequency related to movement of the processing tool.   16. The reserve according to claim 15, wherein the vibration change data creating means further includes window means for dividing and calculating primary data of the vibration or secondary data of vibration obtained from the primary data of the vibration into a predetermined range. Processing equipment.   23. The preliminary processing apparatus according to claim 22, wherein the windows created by the window means overlap each adjacent window, and the primary data of the vibration or the secondary data of the vibration is divided and calculated.   The preliminary processing apparatus according to claim 16 or 17, wherein the calculation means includes machine learning means for extracting the special change data and calculating a discrimination criterion by machine learning.   The preliminary processing apparatus according to claim 15, wherein the processing tool is a cutting tool.   When processing the workpiece by the processing tool, from the vibration change data obtained by the vibration detection means and the vibration change data creation means, the special change data is determined based on a determination criterion obtained by the calculation means, The preliminary processing apparatus according to claim 16 or 17, further comprising a determination unit that determines a processing state by the processing tool.   27. The preliminary machining apparatus according to claim 26, further comprising an abnormal position storage unit that stores a machining position of the workpiece in which an abnormality is detected when an abnormality is detected by the determination unit. A processing tool for processing the workpiece;
A drive shaft for driving the processing tool;
A holding member for holding the workpiece;
An X-axis moving mechanism for moving the holding member relative to the processing tool in the X-axis direction;
A Y-axis moving mechanism for moving the drive shaft relative to the workpiece in the Y-axis direction;
A Z-axis moving mechanism for moving the drive shaft relative to the workpiece in the Z-axis direction;
Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
And a discriminating unit for discriminating data obtained from the vibration detecting unit based on a discrimination standard obtained from the collation result obtained by the collating unit of the preliminary processing apparatus according to claim 15. Processing equipment.   29. The processing apparatus according to claim 28, further comprising discrimination criterion storage means for storing the discrimination criterion. Vibration change data creating means for creating vibration change data related to secondary data of vibration obtained from primary data of vibration detected by the vibration detecting means;
The discriminating means discriminates special change data from vibration change data obtained by the vibration detecting means and the vibration change data creating means when machining the workpiece by the processing tool, based on the discrimination criterion, 30. The processing apparatus according to claim 28 or 29, wherein the processing state is determined.   30. The machining apparatus according to claim 28 or 29, further comprising an abnormal position storage unit that stores a machining position of the workpiece in which an abnormality is detected when an abnormality is detected by the determination unit. Vibration detecting means for detecting vibration during processing of the workpiece by the processing tool;
28. A discriminating unit for discriminating data obtained from the vibration detecting unit based on a discrimination standard obtained from the collation result obtained by the collating unit of the preliminary processing apparatus according to any one of claims 15 to 27. Processing state detection device.   33. The machining state detection device according to claim 32, further comprising discrimination criterion storage means for storing the discrimination criterion. Vibration change data creating means for creating vibration change data obtained from primary data of vibration detected by the vibration detecting means,
The discriminating means discriminates special change data from vibration change data obtained by the vibration detecting means and the vibration change data creating means when machining the workpiece by the processing tool, based on the discrimination criterion, 34. The machining state detection device according to claim 32 or 33, wherein the machining state is discriminated.

Images