Cutting tool wear monitoring method based on evolutionary data clustering analysis

Abstract

The invention discloses a cutting tool wear monitoring method based on evolutionary data clustering analysis. The method is used for solving the technical problem that an existing cutting tool wear monitoring method is poor in practicability. The technical scheme comprises the following steps of collecting sensor signals; extracting feature values, selecting a correlation coefficient calculation method to screen features sensitive to evolution of the tool wear value; constructing a feature matrix in a normalized manner; the method comprises the following steps of: determining an optimal clustering number by using a Cannski-Harabasz index, a Davies-Boulin index and a Silhouette coefficient; and finally, carrying out clustering analysis on two kinds of evolution data of the cutter wear valueand the feature matrix by utilizing an agglomeration hierarchical clustering method; comparing whether the clustering cluster where each element in the feature matrix evolution clustering result is located is the same as the clustering cluster where each element in the tool wear value evolution clustering result is located, to acquire the high coincidence rate of the feature matrix and the element corresponding to the tool wear value in the whole tool wear period so that the practicability is good.

Description

technical field [0001] The invention relates to a cutting tool wear monitoring method, in particular to a cutting tool wear monitoring method based on evolution data cluster analysis. Background technique [0002] Nickel-based superalloy GH4169 is a multi-component complex alloy. Because of its excellent thermal strength, thermal stability and thermal fatigue performance, it is often used in the manufacture of heat-resistant parts such as discs and blades of aerospace engines and gas turbines. However, due to the poor thermal conductivity, severe work hardening, and high affinity of GH4169, it leads to poor machinability, fast tool wear, and deep wear. Its difficult machining has become a problem in the manufacturing industry. [0003] The tool wear value is a typical evolution data, which increases at different rates with the increase of the milling distance, but due to the complexity of the machining process, it is difficult to directly monitor the tool wear state using op...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the shortcomings of poor practicability of existing cutting tool wear monitoring met...

Images