Numerical control system

Abstract

A numerical control system detects a state amount indicating a state of machining operation of a machine tool, creates a characteristic amount that characterizes the state of machining operation fromthe detected state amount, infers an evaluation value of the state of machining operation from the characteristic amount, and detects an abnormality in the state of machining operation on the basis ofthe inferred evaluation value. The numerical control system generates and updates a learning model by machine learning that uses the characteristic amount, and stores the learning model in correlation with a combination of conditions of the machining operation of the machine tool.

Description

technical field [0001] The present invention relates to a numerical control system, in particular to a numerical control system for detecting wear / breakage of a machine tool by switching a learning model. Background technique [0002] In a machine tool (for example, a machining center, a lathe, etc.) that moves a tool relative to a workpiece to process a workpiece, the tool is worn during machining of the workpiece, and the toothed tool may be damaged depending on the situation. If there is a defect in the worn or damaged tool of the machine tool used for processing, the abnormal movement of the spindle will occur during processing, which will have a direct impact on the machining accuracy of the workpiece. Therefore, the operator judges the wear and damage of the tool. When the state of wear and damage exceeds the allowable range, replace the tool. [0003] As a prior art for judging the state of tool wear and damage, for example, Japanese Patent Laying-Open No. 11-267949 ...

AI Technical Summary

Problems solved by technology

[0004] However, even if it is desired to judge the wear and breakage state of the tool based on information that can be observed from the outside during machining, the machining state information observed from the outside when the tool is worn or broken depends on the type of tool used for machining, workpiece material, and spindle. Rotation speed, feed speed, etc. are different, so there is a problem that it is difficult to generate a general-purpose machine learning machine (general-purpose learning model) that can be used in accordance with these various conditions, and it is necessary to detect various state information under various conditions.

Images