关键词: 刀具磨损 数据融合 小波包分解 小波神经网络 遗传神经网络 遗传小波神经网络

Abstract:

A computational intelligent data fusion method for monitoring end mill wear is presented in this paper. The signals of cutting force and vibration are measured with multi-sensors, the cutting force features are extracted with frequency mutation and the vibration features are extracted using wavelet pa ckage decomposition. Several computational intelligent data fusion methods, which are wavelet neural networks, genetic algorithm neural networks （GA-NN）, and wavelet generic algorithm neural networks for predicting the tool wear values are discussed. The experimental results show all of these present ted methods can effectively perform tool wear prediction.

Key words: tool wear;data fusion, wavelet package decomposition, wavelet neural network; genetic neural network, ge-netic wavelet neural network