A method for identifying the tool wear degree of a large CNC milling machine

Abstract

The invention provides a method for identifying the degree of tool wear of a large CNC milling machine. The identification method obtains the vibration time domain signal under the operating state of a large CNC milling machine, and uses the fast Fourier transform to obtain the frequency domain distribution of the vibration signal, and selects the time domain and Multiple statistical characteristic parameters in the frequency domain are used to reduce the dimensionality of the tool wear characteristic parameters based on the diffusion mapping method, and the problem of selecting the scale parameters of the diffusion mapping is determined by using the leave-one-out cross-validation method and the optimal search algorithm; combined with the Nystrom extension and kernel regression algorithm The wear degree of the unknown tool to be tested is identified. The invention can effectively overcome the shortcoming of missing tool wear samples of large-scale numerically controlled milling machines, improve the identification accuracy of the tool wear degree of large-scale numerically controlled milling machines, and reduce maintenance costs and time caused by untimely identification of tool wear.

Description

technical field [0001] The invention belongs to the field of large-scale numerically controlled milling machines, and in particular relates to a method for identifying the degree of tool wear of large-scale numerically controlled milling machines. Background technique [0002] In addition to milling planes, grooves, gear teeth, threads and spline shafts, CNC milling machines can also process more complex profiles, with high production efficiency, and are widely used in the machinery manufacturing industry. Especially large-scale CNC milling machines (such as gantry milling machines), because of their high machining accuracy and production efficiency, are often used in the batch production of large workpieces. [0003] As the most vulnerable parts of large CNC milling machines, cutting tools are particularly important for timely and effective state identification and monitoring. According to statistics, tool wear is the primary cause of milling machine failure, and the resul...

AI Technical Summary

Problems solved by technology

However, for large-scale CNC milling machines, the identification of the tool wear degree still faces the following problems: (1) The processing objects of large-scale CNC milling machines are generally large, which makes it difficult to collect data under different tool wear degrees, and the cost is relatively high. (2) Most of the research methods need to manually determine the value of key parameters (such as the penalty function and scale factor of support vector machine), which is highly subjective. The misdiagnosis rate is high in the identification of the wear degree of CNC milling machine tools

Images