Cutter abrasion loss monitoring method based on simulation feature and signal feature fusion

Abstract

The invention relates to a tool wear loss monitoring method based on simulation feature and signal feature fusion, which comprises the following steps: S1, acquiring an original vibration signal, and measuring the wear loss of a rear tool surface; s2, performing signal preprocessing on the original vibration signal and extracting signal features; s3, performing J-C constitutive model parameter calibration of the first-state material based on stretching, compression and Hopkinson pressure bar experiments; s4, performing J-C constitutive model correction of other state materials except the first state material based on the hardness experiment; s5, acquiring simulation characteristics of the same material in different states; s6, performing feature selection and feature dimension reduction on the signal features and the simulation features to obtain fused low-dimension features; s7, training an LSTM (Long Short Term Memory) model according to the dimensionality-reduced features obtained by feeding each time and the corresponding flank abrasion loss; and S8, the abrasion loss of the rear tool face is obtained after the features obtained through each feeding are input. According to the method, the workload of model correction is reduced, repeated experiments are avoided, and meanwhile the precision of the model can be improved.

Description

Technical field [0001] The present invention relates to a tool wear monitoring technology, and more particularly a method for monitoring tool wear characteristics and signal characteristics simulation fusion. Background technique [0002] The tool will inevitably wear during processing, tool wear can affect the process, resulting in a decline of the quality of surface processing, even when serious accidents occur machining. When the tool reaches the standard blunt, timely replacement of the tool should avoid the use of the tool after the machining of the workpiece abrasion process has decreased surface quality. However, in the process operators often do not know the specific tool wear, can only be judged by the experience of tool wear or use the machine to stop. Currently, the detection processing tool downtime wear of the total process of 20%, 3% to 12% of the production costs and costs related to the tool. In modern processing plants, the process tends to integration, automatio...

AI Technical Summary

Problems solved by technology

In modern processing plants, processing tends to be integrated and automated, and downtime means reduced automation and reduced operating efficiency of the factory, which is very undesirable for modern processing

Images