Tool wear monitoring method based on multi-sensor composite signals

Abstract

The invention relates to a tool wear monitoring method based on multi-sensor composite signals. According to the tool wear monitoring method based on the multi-sensor composite signals, the related signal information of machine-tool tool wear is acquired by the adoption of an acoustic emission sensor and a power sensor, and the defect of the single signal can be overcome by the adoption of the twokinds of signal collection methods. Two kinds of information are scientifically coupled by the adoption of a cloud model algorithm, the characteristic factors of tool wear amount reflected in the signals can be extracted, a model is built through a sparse Bayesian method, and the tool wear amount is forecast; modelling is conducted on data by the adoption of a recognition method based on SBL, andthe width parameters of a SBL model kernel function is optimized by the adoption of a Bayesian matching pursuit algorithm; and the tool wear amount is precisely forecast, and the efficiency and accuracy of tool wear monitoring are improved.

Description

technical field [0001] The invention relates to a tool wear monitoring method based on multiple types of sensor composite signals, belonging to the field of tool wear detection. Background technique [0002] As one of the cores of a smart factory, smart devices have self-identification, self-learning and self-maintenance capabilities for operating status are important features. According to statistics, tool changing and tool setting during processing account for about 20% of the equipment's running time. In addition, the wear and damage of cutting tools have a significant impact on processing quality, processing efficiency, machine tool life and even the personal safety of operators. Therefore, accurate and efficient self-identification and automatic early warning of tool running status are of great significance to improve the intelligence level of machine tools, which can effectively save costs and improve efficiency. [0003] Due to the complexity of the tool wear proces...

AI Technical Summary

Problems solved by technology

The prediction algorithm of artificial neural network, the model is too complex, requires a large number of experimental samples, and the calculation convergence is difficult. Support vector machine can realize the prediction of tool wear under small samples, but it is prone to over-learning phenomenon, and the sparsity of the model is limited. and cannot provide the probability information of the predicted results

Images