Monitoring method based on image features and LLTSA algorithm for tool wear state

Abstract

The invention relates to a monitoring method based on image features and an LLTSA algorithm for a tool wear state. According to the method, an image texture feature extraction technology is introduced into the field of tool wear fault diagnosis, and monitoring for the tool wear state is realized in combination with three flows of ' signal denoising', 'feature extraction and optimization' and 'mode recognition'. The method comprises the steps of firstly, acquiring an acoustic emission signal in a tool cutting process through an acoustic emission sensor, and carrying out signal denoising processing through an EEMD diagnosis; secondly, carrying out time-frequency analysis on a denoising signal through S transformation, converting a time-frequency image to a contour gray-level map, extracting image texture features through a gray-level co-occurrence matrix diagnosis, and then further carrying out dimensionality reduction and optimization on an extracted feature vector through a scatter matrix and the LLTSA algorithm to obtain a fusion feature vector; and finally training a discrete hidden Markov model of the tool wear state through the fusion feature vector, and establishing a classifier, thereby realizing automatic monitoring and recognition for the tool wear state.

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 image features and LLTSA algorithm. Background technique [0002] The cutting tool is one of the most widely used cutting tools in the metal processing process. The degree of tool wear directly affects the accuracy of the machined parts. Forced shutdown, or even cause the operation failure of the entire processing system, bring safety hazards and economic losses, so tool wear status monitoring is an inevitable task to ensure the normal operation of machine tools. [0003] The key to tool wear status monitoring lies in accurate fault feature extraction from monitoring signals. At present, most feature extraction methods construct feature vectors by analyzing various parameters of cutting signals, such as time domain or frequency domain parameters, energy, amplitude etc.; while the image feature extraction technology ...

AI Technical Summary

Problems solved by technology

However, the extracted image features often have the problems of large dimensionality and fuzzy feature selection rules, resulting in redundant information in the feature vector or a lot of important information not being fully applied.

So far, there are no bibliographical reports and practical applications relevant to the method of the present invention

Images