Milling cutter wear prediction method and state recognition method

Abstract

The invention discloses a milling cutter wear prediction method and a state recognition method. The wear prediction method comprises the following steps that firstly, wavelet noise reduction processing is performed on milling vibration data, feature extraction is performed on vibration signals from three aspects including time domain, frequency domain and time domain, after an initial feature vector set is obtained, a correlation coefficient method is used for calculating the correlation between feature vectors and wear amount, and an optimal feature vector set is obtained by screening; then,an average relative error predicted by a least squares support vector machine is defined as a fitness function of an adaptive step size cuckoo search algorithm, and by searching for a nest position, input parameters of the least squares support vector machine are optimized; finally, the wear amount is predicted by using the optimal least square support vector machine. Through comparison with two other hybrid intelligent algorithms, the superiority of an ASCS- LSSVR algorithm is verified.

Description

technical field [0001] The invention belongs to the technical field of mechanical processing, and more specifically relates to a wear prediction method and a state recognition method of a milling cutter. Background technique [0002] At present, the automatic monitoring schemes in the field of tool wear are mainly divided into two categories: direct method and indirect method. The direct method is generally applied to off-line monitoring in the non-processing process. The parameters such as the position and shape of the tool are directly obtained through the sensing device to determine the wear condition of the tool; the indirect method is to measure the indirect indicators such as tool vibration, force, current, and acoustic emission and Establish a correlation relationship with the cutting wear state, so as to obtain the wear degree of the tool. [0003] Although the direct method has high precision, it often has the disadvantages of not being able to guarantee real-time ...

AI Technical Summary

Problems solved by technology

[0007] In view of the above defects or improvement needs of the prior art, the present invention provides a milling cutter wear prediction method and a state identification method, the purpose of which is to solve the technical problem of low modeling accuracy of the existing method

Images