Tool abrasion prediction method

Abstract

The invention relates to the field of machining, in particular to a tool abrasion prediction method based on surface texture feature and multi-sensing signal feature fusion. A cutting signal collecting system comprises a clamping jaw, a workpiece, a turning tool blade, an inner hexagon bolt, a dynamometer sensor, a high-speed camera and a vibration sensor, wherein the clamping jaw and the workpiece are arranged on a chuck; and the turning tool blade, the inner hexagon bolt, the dynamometer sensor, the high-speed camera and the vibration sensor are arranged on a tool bar. The tool bar is arranged in the dynamometer sensor through the inner hexagon bolt, and the vibration sensor is arranged on the outer side of the front end of the tool bar. The workpiece is arranged on the chuck through theclamping jaw. According to the tool abrasion prediction method, the dynamometer sensor, the vibration sensor and the high-speed camera are utilized to build a set of workpiece processed surface texture and multi-sensor cutting signal collecting device, gray histogram equalization processing is carried out on the processed surface texture, and a gray co-occurrence matrix of the preprocessed surface texture is calculated; and the matrix is subjected to extraction of four characteristic quantities including energy, entropy, inertia moment and correlation, and tool abrasion can be monitored.

Description

technical field [0001] The invention relates to the field of mechanical processing, in particular to a tool wear prediction method based on fusion of surface texture features and multi-sensing signal features. Background technique [0002] During the cutting process, tool wear will reduce the surface quality of the workpiece, and will increase the cutting force and cutting temperature during the cutting process. In order to obtain qualified surface quality and avoid unnecessary loss, it is necessary to monitor the tool wear state during cutting. With the development of sensing technology and the rise of the tool monitoring system, the cutting signal in the cutting process is collected in real time, and the time domain and frequency domain feature extraction are performed on the cutting signal to form a feature set, and then the regression analysis is used to predict the tool wear status. a possibility. At present, most of the research on tool wear monitoring is still based...

AI Technical Summary

Problems solved by technology

In addition, the cutting process often includes multiple types of tools and workpiece materials, and it is far from enough to realize tool wear monitoring under specific tool and material combinations

It can be seen that the current research on tool wear monitoring still has limitations. The prediction accuracy of the obtained tool wear monitoring model is not high enough and the prediction model is not universal.

Images