Micro-milling cutter wear state monitoring method based on locally linear embedding method

Abstract

The invention discloses a micro-milling cutter wear state monitoring method based on a locally linear embedding method, which comprises the following steps: acquiring an acceleration signal in a vertical milling cutting process through an acceleration sensor mounted on a main shaft of a vertical milling machine, expressing the acceleration signal as X=[x(1), x(2),..., x(n)], expressing the signal length by n, and extracting the frequency domain characteristic of the signal at the cutting moment; carrying out dimensionality reduction operation on the extracted frequency domain features, and processing the frequency domain features by using a local linear embedding method to obtain three dimensionality-reduced frequency domain feature quantities with strong correlation; then inputting the the method comprises the following steps: firstly, carrying out dimensionality reduction on a tool, then inputting the feature quantity subjected to dimensionality reduction into a BP neural network for training, carrying out grey wolf optimization on the neural network, finally, enabling the neural network to classify signals generated by the tool with different wear degrees by virtue of the extremely strong nonlinear mapping capability of the neural network, and accurately judging the category of an unknown signal. The method is higher in recognition precision of different abrasion states, higher in efficiency and capable of finding out severe abrasion of the cutter in time.

Description

technical field [0001] The invention relates to the technical field of micro-milling tool wear monitoring, in particular to a micro-milling tool wear state monitoring method based on a local linear embedding method. Background technique [0002] With the development of science and technology, people have higher and higher requirements for product refinement. With the rapid development of precision and ultra-precision technology, three-dimensional tiny parts with feature sizes ranging from millimeters to microns have been widely used in aerospace and defense industries. , medical equipment and bioengineering and other key military and civilian fields. This requirement has led to the development of precision machining and micro-milling processing technology. Compared with large systems, microsystems have low energy consumption and facilitate process integration. However, with the gradual reduction of the size of the workpiece and the tool, the wear of the micro-milling cutte...

AI Technical Summary

Problems solved by technology

But the coolant required for the cutting process and the debris generated are not conducive to camera shooting

Images