An improved machine tool health status assessment method and CNC machine tool

Abstract

The invention discloses an improved machine tool health state evaluation method and a numerical control machine tool, and belongs to the field of numerical control machining diagnosis. The improved machine tool health state evaluation method comprises the following steps that (1) operation state information detecting of a target part is conducted on a machine tool which is qualified after being subjected to delivery inspection, and a machine tool health state standard data sample is obtained; (2) a characteristic value of the standard data sample obtained in the step (1) is subjected to normalization processing; (3) normalized data obtained in the step (2) are trained through a support vector data description method, and thus a contrast sample model is obtained; and (4) a machine tool health state data sample is obtained in real time in the machine tool operation process and compared with the contrast sample model obtained in the step (3), and the machine tool real-time health state isobtained. According to the improved machine tool health state evaluation method, the influence of sample random fluctuation during experiment sampling is small, the requirement for the number of experiment times is also greatly reduced, and finally, the obtained contrast sample model has higher reliability and robustness.

Description

technical field [0001] The invention belongs to the field of numerical control machining diagnosis, and more specifically relates to a more scientific and robust method for online assessment of the health status of numerical control machine tools and numerical control machine tools. Background technique [0002] The current health check method for CNC machine tools mostly uses external sensors to obtain the operating status information of CNC machine tools, and then conducts offline analysis and processing of a batch of collected data to obtain the diagnostic results of the machine tool health status. This type of method can only be used for regular detection, and there are many limitations such as the inability to collect multiple signals synchronously, and the inability to obtain valuable signals (such as current signals) inside the CNC system. It can only be used as a means of scientific research, and cannot be integrated into CNC equipment for Industrialized large-scale ...

AI Technical Summary

Problems solved by technology

[0004] The advantage of this method is that it does not require expensive acquisition cards, computers and other external devices, and the acquisition process and health check process are directly integrated into the CNC machine tool, which greatly improves the reliability of data acquisition and the efficiency of health checks, but the disadvantage is that The calculation of the health status of the machine tool depends on the quality of the comparison sample data, and the comparison sample data is the average value of all the health characteristic values ​​collected after repeated experiments after the CNC machine tool leaves the factory, and it is easy to select Affected by the quality of experiments or the normal fluctuation of machine tool status information, the reliability of the machine tool health status assessment is reduced. In addition, the calculation method of the health index also has room for further improvement

Images