Real-time cutter wear prediction method based on wavelet packet decomposition and deep learning

Abstract

The invention belongs to the related technical field of cutter state monitoring. The invention discloses a real-time cutter wear prediction method based on wavelet packet decomposition and deep learning. The method comprises the following steps of: (1), synchronously acquiring related sensor signals in a workpiece machining process, selecting stable signal sections as signal sections to be analyzed, and expanding a signal sample to be analyzed to increase the sample size; carrying out wavelet packet decomposition transformation on the to-be-analyzed signal to obtain a plurality of wavelet packet coefficient two-dimensional matrixes; (2), correspondingly taking the wavelet packet coefficient two-dimensional matrix as the input of a feature extraction CNN model block, splicing the one-dimensional feature matrix output by each feature extraction CNN model block into a longer one-dimensional matrix, performing feature fusion, and establishing a two-layer full-connection network, thereby obtaining a convolutional neural network model; and (3), inputting to-be-analyzed signal data into a convolutional neural network model so as to predict the abrasion loss of the cutter in real time. Thecost can be reduced, and the applicability is high.

Description

technical field [0001] The invention belongs to the technical field related to tool state monitoring, and more specifically relates to a real-time tool wear prediction method based on wavelet packet decomposition and deep learning. Background technique [0002] The state of tool wear will directly affect the surface quality of the machined workpiece, thereby affecting the yield rate of the workpiece. Long-term use of the tool in an excessively worn state will greatly affect the spindle accuracy of the machine tool, resulting in long-term shutdown of the machine tool for maintenance. According to relevant research, by accurately monitoring the state of the machine tool tool, the machine tool spindle speed can be increased by 10% to 50% during processing, the downtime of the machine tool can be reduced by 20%, and the factory can save 10% to 40% of the total cost. Therefore, the tool state The detection system has a good market prospect. [0003] At present, the mainstream me...

AI Technical Summary

Problems solved by technology

At the same time, the prediction method uses PReLU as the activation function of the mathematical model, uses the Adam algorithm as the model optimization algorithm, and uses a supervised learning method to establish the relationship between the target signal and the amount of tool wear by analyzing the relevant signals generated by the machine tool during the machining process. relationship, so as to solve the problem of difficult real-time prediction of tool wear

Images