KR20210060766A - Apparatus for distinguishing process machine tools and method thereof - Google Patents

Abstract

The present invention discloses an apparatus and method for determining a process of a machine tool. The apparatus for determining a process of a machine tool of the present invention comprises: a data input unit receiving shape data of a workpiece; A machine learning unit that provides a probability for determining a process type by machine learning based on shape height data; Process type based on the result of learning through the machine learning unit by forming a Z-Map model based on the shape data of the workpiece input from the data input unit to extract shape height data, and convert the shape height data into 2D data A control unit for determining And an output unit for outputting the process type determined by the control unit to the machine tool.

Description

Machine tool process determination device and its method {APPARATUS FOR DISTINGUISHING PROCESS MACHINE TOOLS AND METHOD THEREOF}

The present invention relates to an apparatus and method for determining a process of a machine tool, and more particularly, to construct a Z-Map model based on shape data of a workpiece, and to construct a learning model through machine learning based on height data. It relates to a process discrimination apparatus and method for a machine tool capable of automatically generating a process with high accuracy by discriminating a process type of a machine.

In general, machine tools are collectively referred to as a device that performs various processing, and various types are known according to the processing range, and representatively, there is a computerized numerical control (CNC) machine tool. These CNC machine tools automatically determine the position of the cutting tool or automatically determine the position of the cutting tool by directly connecting a program that records numerical data that selectively indicates the machining dimension, shape, required tool, and feed speed when cutting a workpiece. Is to perform.

In order to accurately process a desired shape using a machine tool operated through a numerical controller, it is essential to prepare a machining program. Methods for creating this machining program include a manual writing method by a user's manual operation, an interactive program, and a method using machining program creation software such as CAM (Computer Aided Manufacturing).

When a user creates a machining program by hand by looking at the drawing and calculating the movement path of the tool, it is usually used when the shape is simple or only a part of the shape is to be processed simply. The same applies to cases in which the working environment in which the part program generation software can be used is not possible, and the user does not know how to use the part program generation software well.

In the case of processing program creation software such as interactive programs and CAM, the processing shape is complicated, so that the user inputs the processing shape as text into the software installed in the numerical controller (CNC) or PC (Personal Computer), or CAD (Computer Aided Design). ) By inputting data in the form of files such as drawing files and 3D model files, a part program that can be used directly through the part program creation software is created.

The background technology of the present invention is disclosed in Korean Patent Publication No. 10-1996099 (announced on July 4, 2019, cloud programming system and method thereof for machine tools).

An object of the present invention according to an aspect of the present invention is to construct a Z-Map model based on shape data of a workpiece, and construct a learning model through machine learning based on height data to determine the process of a machine tool, thereby providing a process with high accuracy. It is to provide an apparatus and method for determining a process of a machine tool that can be automatically generated.

An apparatus for determining a process of a machine tool according to an aspect of the present invention includes: a data input unit for receiving shape data of a workpiece; A machine learning unit that provides a probability for determining a process type by machine learning based on shape height data; Process type based on the result of learning through the machine learning unit by forming a Z-Map model based on the shape data of the workpiece input from the data input unit to extract shape height data, convert the shape height data into 2D data, and perform learning through the machine learning unit. A control unit for determining And an output unit for outputting the process type determined by the control unit to the machine tool.

In the present invention, the shape data of the workpiece includes 3D shape data of the workpiece.

In the present invention, the control unit is characterized in that after analyzing the edges of the 3D shape data, the points of each edge are connected to form a triangular element network to form a Z-Map model.

In the present invention, the machine learning unit is characterized in that it is configured as a cloud system.

In the present invention, the process type is characterized by including any one of a pocket, a groove, a floor surface, a wall surface, and a contour.

In the present invention, when the tool information is input from the data input unit, the control unit predicts and provides a process parameter to be used in a process.

A method for determining a process of a machine tool according to another aspect of the present invention includes: receiving, by a control unit, shape data of a workpiece from a data input unit; Forming, by the control unit, a Z-Map model based on shape data of the workpiece input from the data input unit; Extracting shape height data from the Z-Map model, converting the shape height data into 2D data, and performing machine learning through a machine learning unit; Determining, by the controller, a result of performing machine learning and determining a process type; And outputting the process type determined by the control unit to the machine tool.

In the present invention, the shape data of the workpiece is characterized in that it includes 3D shape data of the workpiece.

In the present invention, the step of forming a Z-Map model is characterized in that the control unit analyzes the edges of the 3D shape data, and then connects the points of each edge to form a triangular element network to form a Z-Map model. do.

In the present invention, the process type is characterized by including any one of a pocket, a groove, a floor surface, a wall surface, and a contour.

In the present invention, the step of outputting the process type to the machine tool is characterized in that when the tool information is input from the data input unit, the control unit outputs prediction information that predicts a process parameter to be used in the process together.

A machine tool process discrimination apparatus and method according to an aspect of the present invention configure a Z-Map model based on shape data of a workpiece, and construct a learning model through machine learning based on height data to form a machine tool process. By discriminating the type, it is possible to automatically generate a process with high accuracy.

1 is a block diagram showing an apparatus for determining a process of a machine tool according to an embodiment of the present invention.
2 is an exemplary view showing 3D shape data input from a process determination apparatus of a machine tool according to an embodiment of the present invention.
3 is an exemplary view showing shape height data in a process determination apparatus of a machine tool according to an embodiment of the present invention.
4 is a flowchart illustrating a method of determining a process of a machine tool according to an embodiment of the present invention.

Hereinafter, an apparatus and method for determining a process of a machine tool according to the present invention will be described with reference to the accompanying drawings. In this process, the thickness of the lines or the size of components shown in the drawings may be exaggerated for clarity and convenience of description. In addition, terms to be described later are terms defined in consideration of functions in the present invention, which may vary according to the intention or custom of users or operators. Therefore, definitions of these terms should be made based on the contents throughout the present specification.

1 is a block diagram showing a process determination device of a machine tool according to an embodiment of the present invention, Figure 2 is an example showing 3D shape data input from the process determination device of the machine tool according to an embodiment of the present invention Fig. 3 is an exemplary view showing shape height data in a process determination apparatus for a machine tool according to an embodiment of the present invention.

As shown in FIG. 1, the process determination apparatus of a machine tool according to an embodiment of the present invention may include a data input unit 10, a machine learning unit 30, a control unit 20, and an output unit 40. have.

The data input unit 10 may receive shape data of a workpiece for determining the type of process in the machine tool 50 and provide it to the control unit 20.

Here, the shape data of the workpiece may include 3D shape data of the workpiece as shown in FIG. 2.

The machine learning unit 30 may provide a probability for determining the type of process by machine learning based on shape height data.

Here, the machine learning unit 30 may perform machine learning by receiving 2D data of shape height data. In addition, by configuring the machine learning unit 30 as a cloud system, it is possible to provide high-performance results through the cloud system and enhance the learning effect even if the process determination device is not of high specification.

The controller 20 may extract shape height data as shown in FIG. 3 by forming a Z-Map model based on the 3D shape data of the workpiece input from the data input unit 10.

Here, the controller 20 may analyze an edge based on surface information of 3D shape data, and then connect points of each edge based on the point data to form a triangular element network to form a Z-Map model.

Thereafter, the control unit 20 may convert the shape height data into 2D data and input it to the machine learning unit 30 to receive the result of performing the learning, and determine the process type having the highest probability.

Here, the process type may include any one of a pocket, a groove, a bottom surface, a wall surface, and a contour.

Meanwhile, when tool information is input from the data input unit 10, the control unit 20 may predict and provide a process parameter to be used in a process according to a process type.

The output unit 40 may output the process type determined by the control unit 20 to the machine tool 50 to generate a machine tool processing program.

As described above, according to the process determination apparatus of a machine tool according to an embodiment of the present invention, a Z-Map model is constructed based on shape data of a workpiece, and a learning model is constructed through machine learning based on height data. By discriminating the process type of the machine tool, it is possible to automatically generate processes with high accuracy.

4 is a flowchart illustrating a method of determining a process of a machine tool according to an embodiment of the present invention.

As shown in FIG. 4, in the process determination method of a machine tool according to an embodiment of the present invention, first, the control unit 20 receives shape data of the workpiece from the data input unit 10 (S10).

Here, the shape data of the workpiece may include 3D shape data of the workpiece as shown in FIG. 2.

After receiving the 3D shape data of the workpiece in step S10, the control unit 20 forms a Z-Map model based on the input shape data of the workpiece (S20).

Here, the controller 20 may analyze an edge based on surface information of 3D shape data, and then connect points of each edge based on the point data to form a triangular element network to form a Z-Map model.

After forming the Z-Map model in step S20, the controller 20 extracts shape height data from the Z-Map model as shown in FIG. 3 (S30).

After extracting the shape height data in step S30, the controller 20 converts the shape height data into 2D data and inputs it to the machine learning unit 30 to perform machine learning (S40).

After machine learning is performed through the machine learning unit 30 in step S40, the control unit 20 may receive the result of performing the machine learning and determine a process type having the highest probability (S50).

Here, the process type may include any one of a pocket, a groove, a bottom surface, a wall surface, and a contour.

After determining the process type in step S50, the control unit may output the process type to the machine tool 50 through an output unit to generate a machine tool processing program.

Meanwhile, when tool information is input from the data input unit 10, the control unit 20 may also output prediction information that predicts a process parameter to be used in a process according to a process type.

As described above, according to the process determination method of a machine tool according to an embodiment of the present invention, a Z-Map model is constructed based on shape data of a workpiece, and a learning model is constructed through machine learning based on height data. By discriminating the process type of the machine tool, it is possible to automatically generate processes with high accuracy.

The implementation described herein may be implemented in, for example, a method or process, an apparatus, a software program, a data stream or a signal. Although discussed only in the context of a single form of implementation (eg, only as a method), the implementation of the discussed features may also be implemented in other forms (eg, an apparatus or program). The device may be implemented with appropriate hardware, software and firmware. The method may be implemented in an apparatus such as a processor, which generally refers to a processing device including, for example, a computer, a microprocessor, an integrated circuit or a programmable logic device, or the like. Processors also include communication devices such as computers, cell phones, personal digital assistants (“PDAs”) and other devices that facilitate communication of information between end-users.

Although the present invention has been described with reference to the embodiments shown in the drawings, this is only illustrative, and those of ordinary skill in the field to which the technology pertains, various modifications and other equivalent embodiments are possible. I will understand.

Therefore, the true technical protection scope of the present invention should be determined by the following claims.

10: data input unit
20: control unit
30: Machine Learning Department
40: output
50: machine tool

Claims (11)

A data input unit for receiving shape data of the workpiece;
A machine learning unit that provides a probability for determining a process type by machine learning based on shape height data;
A result of learning through the machine learning unit by forming a Z-Map model based on the shape data of the workpiece input from the data input unit to extract the shape height data, converting the shape height data into 2D data, and A control unit that determines the type of process based on; And
And an output unit for outputting the process type determined by the control unit to a machine tool.
The machine tool process discrimination apparatus according to claim 1, wherein the shape data of the workpiece includes 3D shape data of the workpiece.
The process of claim 2, wherein the control unit analyzes the edges of the 3D shape data and connects the points of the edges to form a triangular element network to form the Z-Map model. Device.
The apparatus of claim 1, wherein the machine learning unit comprises a cloud system.
The machine tool process discrimination apparatus according to claim 1, wherein the process type includes any one of a pocket, a groove, a bottom surface, a wall surface, and a contour.
The apparatus of claim 1, wherein the control unit predicts and provides a process parameter to be used in a process when tool information is input from the data input unit.
Receiving, by the control unit, shape data of the workpiece from the data input unit;
Forming, by the control unit, a Z-Map model based on shape data of the workpiece input from the data input unit;
Performing machine learning through a machine learning unit by the control unit extracting shape height data from the Z-Map model and converting the shape height data into 2D data;
Determining a process type by receiving, by the control unit, a result of performing machine learning; And
And outputting the process type determined by the control unit to a machine tool.
The method of claim 7, wherein the shape data of the workpiece includes 3D shape data of the workpiece.
The method of claim 8, wherein the forming of the Z-Map model comprises: after the control unit analyzes the edges of the 3D shape data, points of the edges are connected to form a triangular element network to form the Z-Map model. Process determination method of a machine tool, characterized in that.
The method of claim 7, wherein the process type includes any one of a pocket, a groove, a bottom surface, a wall surface, and a contour.
The method of claim 7, wherein the outputting of the process type to the machine tool comprises outputting prediction information that predicts a process parameter to be used in the process when the tool information is input from the data input unit by the control unit. How to determine the process of the machine.

Images