Tool abrasion state monitoring method based on vibration signal and Stacking ensemble model

Abstract

The invention discloses a tool abrasion state monitoring method based on a vibration signal and a Stacking ensemble model. The vibration signal of a machine tool spindle in the machining process is utilized, and the vibration signal is subjected to feature extraction through time-domain analysis, frequency-domain analysis and ensemble empirical mode decomposition (EEMD); then extracted features are screened through a Relief F-SVM algorithm to obtain an optimal feature set; the width of a tool abrasion blade belt serves as the abrasion label value, and an ensemble monitoring model is built based on a Stacking ensemble strategy through the optimal feature set and the abrasion label value; and after the model is built, the vibration signal in the machining process is monitored and processed to obtain the signal feature set to be input into the ensemble monitoring model, and the tool abrasion label value, namely the tool abrasion state is obtained. The tool abrasion state can be monitoredbased on the vibration signal and the Stacking ensemble model.

Description

technical field [0001] The invention relates to the technical field of tool wear state monitoring, in particular to a tool wear state monitoring method based on a vibration signal and a Stacking integrated model. Background technique [0002] Modern manufacturing is gradually developing towards intelligence, and it is particularly important to perceive the performance status of the main components of CNC machine tools in the process of processing. The monitoring of the tool wear state is very important in the machining process, and the tool wear is very important to the surface quality and dimensional accuracy of the machined workpiece. Therefore, the state assessment of tool wear has become an important research topic, but what is more important is how to accurately and stably fit or predict the wear value of a brand-new tool. Because, predicting the wear value too high may lead to waste of tool material, while predicting the wear value too low will increase the defective ...

AI Technical Summary

Problems solved by technology

Support vector machine (SVM) is the most commonly used intelligent algorithm for state recognition. It has a solid theoretical foundation and is suitable for small sample state classification. However, SVM has difficulties in solving multi-classification problems and is difficult to implement for large-scale training samples. The decision tree model is simple, The algorithm is low in complexity and reliable in statistical testing, but the decision tree classification result may be unstable; the naive Bayesian algorithm has stable classification efficiency and can handle multi-classification tasks, but it needs to assume a priori probability, and the prior probability model may lead to poor results

However, due to the increasingly complex working conditions, a single artificial intelligence technology cannot meet the precision requirements

Images