A tool wear monitoring method based on multi-sensor current signals

Abstract

A tool wear monitoring method based on multi-sensor current signals. First, current sensors are used to collect motor current signals of different axes during tool machining, and time-domain analysis and wavelet packet energy spectrum analysis are used to extract energy features of multi-sensor current signals. , and then use the distance evaluation method to calculate the feature sensitivity, and select the features with high sensitivity to the change of the tool state according to the ranking of the sensitivity; then, based on the quantization series adaptive scalarization method of the Lloyds algorithm, scalarize the selected features ;Finally, use the initial processing data of the tool to construct the DHMM monitoring model of the normal state of the tool, and use the data in the severe wear state to construct the DHMM monitoring model of the severe wear state of the tool. After inputting the monitoring data into these two models, the state monitoring result is obtained, namely the maximum likelihood estimation Value, by comparing the size of the maximum likelihood estimation value output by the two models, the monitoring of the tool wear state is realized.

Description

technical field [0001] The invention relates to the technical field of tool wear state monitoring, in particular to a tool wear monitoring method based on multi-sensor current signals. Background technique [0002] As one of the main processing methods in the manufacturing industry, cutting has a great impact on improving the manufacturing level and efficiency. It is becoming increasingly important to carry out state monitoring for the cutting process of CNC machine tool automation production line. As the direct working part of the cutting tool, monitoring its working status, that is, the wear of the tool is one of the important tasks in the automatic production line. In the automatic production line, tool wear will affect the processing accuracy of the workpiece, resulting in out-of-tolerance or waste processing of the workpiece, causing the machine tool to vibrate or be forced to stop, and even cause the operation failure of the entire processing system in severe cases, r...

AI Technical Summary

Problems solved by technology

This will lead to two problems: on the one hand, the tools that have not been scrapped are replaced in advance, resulting in the waste of tools;

Due to quality fluctuations in the tool forming process, tool wear monitoring is required. Tool wear monitoring based on the initial state of the tool can reflect the tool change process, but the initial processing data of the tool is less, how to perform tool wear in the case of a small sample Monitoring is an urgent problem

Images