Tool wear detection method

Abstract

The invention relates to a numerical control technology and a neural network technology, in particular to a tool wear detection method. The method comprises the following steps: firstly, collecting vibration and acoustic emission signals in different axial directions during milling of a high-speed cutter, and carrying out data preprocessing; then, adopting an improved 3-K-Means clustering algorithm to cluster three wear state intervals of the cutter, proposing a multi-selection multi-hidden-layer neural network structure to carry out feature learning on the three wear state intervals, and adopting Softmax for classification; and finally, performing parameter fine adjustment on the whole deep network by adopting stochastic gradient descent, and establishing a tool wear detection model. Experimental results show that the accuracy rate of the method provided by the invention on tool wear detection is as high as 95%.

Description

technical field [0001] The invention relates to numerical control technology and neural network technology, in particular to a tool wear detection method. Background technique [0002] In the process of high-speed milling, the wear condition of the tool is extremely complicated, and it is difficult to detect the wear state of the tool through the traditional artificial model method. How to solve this problem through a more effective method has become a research hotspot in the field of intelligent machining tools. In the process of high-speed milling, it is difficult to detect the state of tool wear, and severe tool wear will affect machining accuracy and product quality. [0003] The traditional method mainly relies on the cutting force coefficient to analyze the tool wear, needs to install an additional force measuring device, and interferes with the processing, so there are inevitable problems of human factors. At the same time, the existing shallow models are more for an...

AI Technical Summary

Problems solved by technology

In the process of high-speed milling, it is difficult to detect the state of tool wear, and severe tool wear will affect machining accuracy and product quality

[0003] The traditional method mainly relies on the cutting force coefficient to analyze tool wear, needs to install additional force measuring devices, and interferes with processing, so there are inevitable problems of human factors

At the same time, the existing shallow models are more for analysis and discrimination of a certain type or a certain signal, so it is very easy to fall into local optimum. In order to solve the problems of weak learning ability and weak generalization ability of shallow models, The present invention proposes a tool wear detection method based on 3-KMMBS

Images