Cutter wear monitoring method based on physical information fusion

Abstract

The invention discloses a cutter wear monitoring method based on physical information fusion, which can accurately diagnose and predict the current cutter wear state in the machining process and prompt a machining system to replace a cutter in time. The method comprises the following steps: 1, collecting processing information and constructing a training data set; 2, constructing and training a physical model; 3, designing a pyramid data driving model based on the frequency spectrum of the cutting signal; 4, a physical information model is constructed and trained, and physical information is introduced through a multi-layer attention mechanism to guide feature extraction of the model; and 5, monitoring tool wear by using the trained physical information model. The tool wear can be monitored stably and accurately under the unknown working condition, so that the machining error is compensated, and the loss caused by over-wear of the tool is reduced.

Description

technical field [0001] The invention relates to the field of tool wear monitoring, in particular to a tool wear monitoring method based on physical information fusion. Background technique [0002] In recent years, with the development of technology, the complexity and precision of processing have been greatly improved. The health of the tool directly affects the quality of the milling process and the product. To ensure machining accuracy, machining reliability and personnel safety, tool wear needs to be monitored during the milling process. Although the related tool wear monitoring research has been very extensive, the existing models can only achieve excellent performance under known machining conditions, but cannot be generalized to other machining scenarios, so the existing research results still cannot be applied to actual machining. in the process. [0003] According to different theoretical foundations, tool wear models are roughly divided into physical models and ...

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to solve the deficiencies of physical models and data-driven models in tool wear monitoring, and proposes a tool wear monitoring method based on physical information fusion with small errors, good real-time performance, and easy deployment, in order to be able to perform in unknown working conditions Stable and accurate monitoring of tool wear, so as to compensate for machining errors and reduce losses caused by excessive tool wear

Images