JP2014169961A - Tool inspection method and tool inspection apparatus - Google Patents

Abstract

A tool inspection method for inspecting a tool with high accuracy by a simple method is provided.
An image information acquisition step of capturing a blade edge of a tool and acquiring image information, a contour extraction step of extracting a contour of the tool blade edge from the image information, a straight line portion KI, MJ, and a curved portion IJ A contour dividing step for dividing the linear section into a plurality of sections, a straight section processing step for calculating a distance between the straight sections KI, MJ and the ideal straight lines AG, BG in each section, and a curved section IJ. A straight line that divides into a plurality of sections and determines the state of the straight line portions KI and MJ based on the distance calculated in the straight line portion processing step and the curve portion processing step that calculates the differential value of the curvature of the curved portion IJ in each section. And a curve portion state determination step for determining the state of the curve portion IJ based on the differential value calculated in the curve portion processing step.
[Selection] Figure 8

Description

  The present invention relates to a tool inspection method and a tool inspection apparatus.

  Patent Document 1 discloses a method for detecting a shape defect of a tool by scanning a line entering a minute amount from the outer peripheral shape drawn by a ridge line with a laser focus displacement meter and detecting irregularities on the scanning line. Yes.

  Further, in Patent Document 2, as a method of inspecting the state of the cutting tool, when the cutting tool is first positioned at the inspection position, the first position and the first tip position of the cutting tool are stored, and the cutting tool is stored. When the second positioning is performed at the inspection position, the second position and the second tip position of the cutting tool are memorized, and the difference between the first tip position and the second tip position and between the first position and the second position are stored. It is disclosed that the amount of wear of a cutting tool is obtained based on the amount of displacement.

JP 9-2108030 A JP 2010-162671 A

  However, since the method described in Patent Document 1 is for inspecting a tool defect by scanning with a laser beam, the apparatus becomes large and the time required for the inspection also becomes long.

  Moreover, since the method described in Patent Document 2 needs to position the cutting tool at a specific position, the inspection accuracy is affected by the positioning accuracy of the cutting tool. In addition, the time required for positioning of the cutting tool becomes longer.

  The present invention has been made in view of the above problems, and an object thereof is to inspect a tool with high accuracy by a simple method.

  In the tool inspection method according to the present invention, an image information acquisition step of capturing a blade edge of a tool and acquiring image information, a contour extraction step of extracting a contour of the tool blade edge from the image information, and the contour as a straight line portion. A contour dividing step for dividing the curved portion into a curved portion, a straight portion processing step for dividing the straight portion into a plurality of sections, and calculating a distance between the straight portion and the ideal straight line in each section, and dividing the curved portion into a plurality of sections. A curve portion processing step for calculating a differential value of the curvature of the curve portion in each section, and a straight portion state determination step for determining the state of the straight portion based on the distance calculated in the straight portion processing step. And a curve portion state determination step for determining the state of the curve portion based on the differential value calculated in the curve portion processing step.

  According to the present invention, the contour of the cutting edge of the tool extracted from the image information is divided into a straight line part and a curved line part, and the state is determined based on the distance between the straight line part and an ideal straight line. Since the state is determined based on the value, the tool can be inspected with high accuracy by a simple method.

It is a schematic block diagram of the tool inspection apparatus which concerns on embodiment of this invention. It is a figure which shows the image data acquired with the camera. It is a figure which shows one process of image processing. It is a figure which shows one process of image processing. It is a figure which shows one process of image processing. It is a figure which shows one process of image processing. It is a figure which shows one process of image processing. It is a figure which shows one process of image processing. It is the elements on larger scale which show one process of image processing. It is a graph which shows the distance d of each area in the 1st straight line outline KI. It is a figure which shows one process of image processing. It is a graph which shows the curvature k of each area in the curve outline part IJ. It is a graph which shows the differential value (DELTA) k of the curvature k of each area in the curve outline part IJ. It is a graph which shows the moving average of distance d of each area in the 1st straight line outline KI. It is a graph which shows the movement dispersion | distribution of the distance d of each area in the 1st linear outline part KI. It is a graph which shows movement dispersion | distribution of the differential value (DELTA) k of the curvature k of each area in the curve outline part IJ. It is a graph which shows the differential value (DELTA) k of the curvature k of each area in the curve outline part IJ.

  Embodiments of the present invention will be described below with reference to the drawings.

  A tool inspection apparatus 100 according to an embodiment of the present invention is an apparatus that inspects tool chips for defects. In this embodiment, a case where the inspection target is a throw-away tip of various tools will be described.

  As shown in FIG. 1, the tool inspection apparatus 100 includes a camera 1 serving as an image information capturing unit that captures image data (image information) by photographing a cutting edge of a throw-away tip mounted on a processing apparatus, and a camera 1. And a computer 2 that performs image processing on the acquired image data and determines the state of the throw-away chip. The camera 1 is attached to a processing apparatus. The computer 2 may be provided adjacent to the processing device, or may be provided at a location away from the processing device.

  The computer 2 includes a display 21 as a display unit capable of displaying image data, and a keyboard 22 and a mouse 23 as input units capable of inputting an instruction from a user.

  Next, the throw-away tip inspection method will be described.

  The cutting edge of the throw-away tip mounted on the processing apparatus is photographed using the camera 1 to acquire image information (image information acquisition step).

  The image data acquired by the camera 1 is read by the computer 2 and displayed on the display 21 as shown in FIG.

  In the computer 2, image processing of the image data acquired by the camera 1 and determination of the state of the throw-away chip are performed. Hereinafter, the procedure will be described.

  First, as shown in FIG. 3, the contour of the blade tip of the throw-away tip is extracted from the image data (contour extraction step). As can be seen from FIG. 3, the cutting edge contour is composed of two opposing linear contours 31 and 32 and a curved contour 33 connecting the two linear contours. The cutting edge contour is divided into two straight portions and a curved portion connecting the two straight portions by the following method.

  As shown in FIG. 4, straight lines AG and BG along the two straight contours 31 and 32 of the blade edge contour are extracted using the Hough transform. Point G is the intersection of line AG and line BG. The straight lines AG and BG are ideal straight lines of the edge contour.

  As shown in FIG. 5, the straight line AG is extracted by rotating α degrees counterclockwise about the point G to extract the straight line CG, and the intersection of the straight line CG and the edge contour is defined as a point E. Further, the straight line BG is rotated clockwise by α degrees around the point G to extract the straight line DG, and the intersection of the straight line DG and the edge contour is set as a point F. The angle α is 2 to 3 degrees.

  As shown in FIG. 6, the circle center O of the arc EF is extracted from the bisector GH of ∠AGB and the arc EF of the edge contour.

  As shown in FIG. 7, a perpendicular line is drawn from the point O to the straight line AG, and an intersection point between the perpendicular line and the edge contour is defined as a point I. Further, a perpendicular line is drawn from the point O to the straight line BG, and the intersection of the perpendicular line and the edge contour is defined as a point J.

  As shown in FIG. 8, the position of the predetermined length L from the point I in the linear outline 31 is set as the point K, and the inspection region KI is determined. In addition, the position of the predetermined length L from the point J in the linear outline 32 is set as the point M, and the inspection region MJ is determined. As described above, the cutting edge contour is divided into the first straight contour portion KI, the second straight contour portion MJ, which are two straight portions, and the curved contour portion IJ, which is a curved portion (contour dividing step). .

  Next, as shown in FIG. 9, the first straight contour portion KI is equally divided into m and divided into a plurality of sections (one section length: L / m). In each section, the first straight contour section KI and the ideal straight line are divided. The distance d from the AG is calculated (straight line portion processing step). If there is a defect in the first straight line outline KI, the first straight line outline KI does not coincide with the ideal straight line AG, and a distance d corresponding to the size of the defect is generated between the first straight line outline KI and the ideal straight line AG. The distance d accurately represents a defect existing in the first straight outline KI. Since the distance d varies among the sections, it is desirable to calculate the distance d for each section as an average value of a plurality of distances d in the section. In FIG. 9, the defect of the first straight outline KI is exaggerated.

  FIG. 10 is a graph showing the distance d of each section. The horizontal axis of FIG. 10 represents the section of the first straight contour KI (m = 90), the vertical axis is the distance d, and the unit is a pixel. By expressing the distance d of each section in a graph, the state of the first straight contour KI can be visually grasped.

  Similarly to the first straight contour portion KI, the second straight contour portion MJ is also divided into a plurality of sections, and the distance d between the second straight contour portion MJ and the ideal straight line BG is calculated in each section. The distance d of each section is represented by a graph.

  For the curved contour portion IJ, as shown in FIG. 11, ∠IOJ is β degrees, and the curved contour portion IJ is equally divided into n sections for each angle β / n, and is divided into a plurality of sections. The radius R is calculated. A curvature k (= 1 / R) is calculated from the radius R, and a differential value Δk of the curvature k is calculated (curve portion processing step). If a defect exists in the curved contour portion IJ, the curved contour portion IJ does not coincide with a perfect circle that is an ideal curve. Since the curvature k is the reciprocal of the radius and indicates the degree of bending with respect to a perfect circle, it accurately represents a defect existing in the curved contour portion IJ. Further, by differentiating the curvature k, the change in the degree of bending of the curved contour portion IJ with respect to the perfect circle is emphasized. Since the curvature k varies among the sections, it is desirable to calculate the curvature k for each section as an average value of a plurality of curvatures k in the section.

  FIG. 12 is a graph showing the curvature k of each section. The horizontal axis of FIG. 12 represents the section of the curved contour portion IJ (n = 450), and the vertical axis is the curvature k. FIG. 13 is a graph showing the differential value Δk of the curvature k of each section. The horizontal axis in FIG. 13 represents the section of the curved contour portion IJ (n = 450), and the vertical axis represents the differential value Δk. By expressing the curvature k and the differential value Δk of each section in a graph, the state of the curved contour portion IJ can be visually grasped.

  Below, the determination method of the state of the 1st straight line outline part KI, the 2nd straight line outline part MJ, and the curve outline part IJ is demonstrated.

  About the 1st straight line outline part KI, a state is judged based on distance d of each section (straight line part state judging process). The determination method will be described in detail below.

  The moving average and moving variance of the distance d of each section in the first straight line outline KI are calculated. A method for calculating the moving average and moving variance will be described with a specific example. For example, when the distance d of each section is 1, 3, 5, 2, 6, 8, 9, and the moving average and moving variance of three consecutive sections are calculated, the moving average is 3.0, 3.3, 4.3, 5.3, and 7.7, and the moving variance (the value obtained by dividing the sum of squares of the deviation from the average value by the number of sections 3) is 2.7, 1.6, 3.3, 6.2, and 1.6.

  FIG. 14 is a graph showing the moving average of the distance d of each section in the first straight line outline KI, and FIG. 15 is a graph showing the movement variance of the distance d of each section in the first straight line outline KI.

  The determination of the state of the first straight outline KI is performed based on a comparison between the moving average and moving variance of the distance d and a predetermined moving average reference value and moving variance reference value.

  A method for setting the moving average reference value will be described. First, image data obtained by photographing the cutting edge of an unused throw-away tip with the camera 1 is processed in the above-described contour extracting step, contour dividing step, and straight line portion processing step. Thereby, distance d of each section in the 1st straight outline part KI is obtained about the cutting edge of an unused throw away tip. Then, the moving average of the distance d of each section is calculated. A moving average reference value is set based on the moving average thus obtained. For example, the moving average reference value is set by multiplying the maximum value of the obtained moving average by a predetermined coefficient. The moving average reference value is stored in advance in the storage unit of the computer 2. The dotted line shown in FIG. 14 is the moving average reference value.

  The moving dispersion reference value is also set by a similar method. The dotted line shown in FIG. 15 is the moving dispersion reference value. The moving average reference value and the moving variance reference value are threshold values for determining the state of the first straight contour KI, and are arbitrarily set according to the accuracy required for the product.

  The determination of the state of the first straight line outline KI is performed by calculating the position, area, and height at which the moving average and moving variance exceed the moving average reference value and moving variance reference value, respectively, and determine the degree of loss from the calculation results. To do. For example, defect levels 1 to 5 are set in advance according to the degree of defect, and when the defect level 5 is reached, the throw-away tip is determined to have a lifetime.

  The determination of the state of the second straight contour portion MJ is performed by the same method as that for the first straight contour portion KI.

  As for the curved contour portion IJ, the state is determined based on the differential value Δk of the curvature k of each section (curved portion state determining step). The determination method will be described below.

  The movement variance of the differential value Δk of the curvature k of each section in the curved contour portion IJ is calculated. The calculation method of the movement variance is the same method as that of the first straight contour KI. FIG. 16 is a graph showing the movement variance of the differential value Δk of the curvature k of each section in the curved contour portion IJ.

  The determination of the state of the curved contour portion IJ is performed based on a comparison between the movement variance of the differential value Δk and a predetermined movement variance reference value. The movement dispersion reference value is set using an unused throw-away tip, as with the first straight line outline KI. The moving dispersion reference value is stored in advance in the storage unit of the computer 2. The dotted line shown in FIG. 16 is the moving dispersion reference value.

  The determination of the state of the curved contour portion IJ is performed by calculating the position, area, and height at which the movement variance exceeds the movement variance reference value, and determining the degree of loss from the calculation result. For example, defect levels 1 to 5 are set in accordance with the degree of defect, and when the defect level 5 is reached, the throw-away tip is determined to have a lifetime.

  Further, the curved contour portion IJ may be performed based on a comparison between the differential value Δk and a predetermined reference differential value. The reference differential value is set using an unused throw-away tip. A dotted line shown in FIG. 17 is a reference differential value. Since the differential value Δk indicates a change in the degree of bending of the curved contour portion IJ, the state of the curved contour portion IJ can be determined without using the moving variance of the differential value Δk.

  As for the curved contour portion IJ, similarly to the first straight contour portion KI and the second straight contour portion MJ, the moving average of the differential value Δk of the curvature k of each section is calculated, and the moving average is predetermined. The state may be determined based on a comparison with the moving average reference value.

  The above-described image processing of the image data acquired by the camera 1 and determination of the state of the throw-away chip are automatically executed by software stored in the computer 2. As a result, if it is determined that the throw-away tip has reached the end of its life, a notification that prompts replacement is issued.

  The image processing of the image data and the determination of the state of the throw-away tip may be performed when the usage time of the throw-away tip reaches a predetermined time or when the number of uses reaches a predetermined number.

  Each reference value is preferably not applied every time the throw-away tip is replaced, but commonly applied to the same type of throw-away tip.

  According to the above embodiment, there exist the effects shown below.

  In the present embodiment, the contour of the tip of the throw-away tip extracted from the image data is divided into a first straight contour portion KI, a second straight contour portion MJ, and a curved contour portion IJ. The state of the two straight contour portions MJ is determined based on the distance from the ideal straight line, and the state of the curved contour portions IJ is determined based on the differential value Δk of the curvature k. Therefore, the tool inspection apparatus 100 does not become large, and since there is no need to position the throw-away tip at a specific position, the tool can be inspected with high accuracy by a simple method.

  In addition, since the reference value used as a reference for determination is set in advance using an unused throw-away tip, the tool can be inspected at high speed and with high accuracy simply by processing one image acquired by the camera 1. can do.

  Further, since the state of the blade tip of the throw-away tip is determined by being divided into three parts, a first straight contour part KI, a second straight contour part MJ, and a curved contour part IJ, the state of each part is determined by a method suitable for the part. It can be determined, and the position and degree of the defect can be specified.

  In the past, skilled techniques were required to determine tool life. When not relying on skilled technology, tools were changed at a safe number of uses. However, according to the present embodiment, it is possible to automatically determine the tool life simply by photographing the cutting edge of the tool, so that no skill is required and the tool can be used up to the true life. And cost can be reduced.

Below, the modification of the said embodiment is shown.
(1) For the first straight contour KI, in addition to the above-described determination method, the distance d of each section is calculated for the cutting edge of an unused throw-away tip, and a reference value is set based on the distance d. The state may be determined based on a comparison with a reference value. The same applies to the second straight outline MJ.
(2) For the first straight line outline KI, the comparison with the reference value set using an unused throw-away tip is not performed, the magnitude of the distance d in each section, and the moving average of the distance d in each section And the state may be determined based on at least one of the movement variance of the distance d of each section. The same applies to the second straight outline MJ.
(3) For the curved contour portion IJ, in addition to the above-described determination method, the differential value Δk of the curvature k of each section is calculated for the cutting edge of the unused throw-away tip, and the reference value is set based on the differential value Δk Then, the state may be determined based on the comparison with the reference value.
(4) For the curve contour portion IJ, the comparison with the reference value set using an unused throw-away tip is not performed, the magnitude of the differential value Δk of the curvature k of each section, the curvature k of each section The state may be determined based on at least one of a moving average of the differential value Δk and a moving variance of the differential value Δk of the curvature k of each section.

  The embodiment of the present invention has been described above. However, the above embodiment only shows a part of application examples of the present invention, and the technical scope of the present invention is limited to the specific configuration of the above embodiment. Absent.

1 Camera (Image information acquisition means)
2 Computer 100 Tool inspection device 31, 32 Straight outline 33 Curved outline

Claims (7)

An image information acquisition step for capturing the image information by photographing the cutting edge of the tool;
A contour extraction step of extracting the contour of the cutting edge of the tool from the image information;
A contour dividing step of dividing the contour into a straight line portion and a curved portion;
A straight line portion processing step of dividing the straight line portion into a plurality of sections and calculating a distance between the straight line portion and the ideal straight line in each section;
A curved section processing step of dividing the curved section into a plurality of sections and calculating a differential value of the curvature of the curved section in each section;
A linear portion state determination step of determining a state of the linear portion based on the distance calculated in the linear portion processing step;
A curve portion state determination step for determining the state of the curve portion based on the differential value calculated in the curve portion processing step;
A tool inspection method comprising: The straight portion state determining step determines the state of the straight portion based on a comparison between the distance calculated in the straight portion processing step and a predetermined reference value.
The curve portion state determining step determines the state of the curve portion based on a comparison between a differential value calculated in the curve portion processing step and a predetermined reference value. The tool inspection method as described.   The straight line portion state determining step calculates a moving average of the distance calculated in the straight portion processing step, and determines the state of the straight portion based on a comparison between the moving average and a predetermined moving average reference value. The tool inspection method according to claim 1 or 2, wherein the determination is made.   The straight line portion state determining step calculates the movement variance of the distance calculated in the straight portion processing step, and determines the state of the straight portion based on a comparison between the movement variance and a predetermined movement dispersion reference value. The tool inspection method according to any one of claims 1 to 3, wherein determination is made.   The curve portion state determination step calculates the movement variance of the differential value calculated in the curve portion processing step, and based on a comparison between the movement variance and a predetermined movement variance reference value, the state of the curve portion The tool inspection method according to any one of claims 1 to 4, wherein the tool inspection method is determined.   6. The tool inspection method according to claim 2, wherein the reference value is set using image information acquired by photographing a cutting edge of an unused tool. Image information acquisition means for capturing the image information by photographing the cutting edge of the tool;
Contour extracting means for extracting the contour of the cutting edge of the tool from the image information;
Contour dividing means for dividing the contour into a linear portion and a curved portion;
A straight line section processing means for dividing the straight line section into a plurality of sections and calculating a distance between the straight line section and the ideal straight line in each section;
A curved section processing means for dividing the curved section into a plurality of sections and calculating a differential value of a curvature of the curved section in each section;
Straight part state determining means for determining the state of the straight part based on the distance calculated in the straight part processing step;
A curve portion state determining means for determining the state of the curve portion based on the differential value calculated in the curve portion processing step;
A tool inspection apparatus comprising: