BP-Neural-Network-Based Tool Wear Monitoring by Using Wavelet Decomposition of the Power Spectrum
摘要
In a drilling process, the power spectrum of the drilling force is related to the tool wear and is widely applied in the monitoring of tool wear. But the feature extraction and identification of the power spectrum have always been an unresolved difficult problem. This paper solves it through decomposition of the power spectrum in multilayers using wavelet transform and extraction of the low frequency decomposition coefficient us the envelope information of the power spectrum. Intelligent identification of the tool wear status is achieved in the drilling process through fusing the wavelet decomposition coefficient of the power spectrum by using a BP ( Back Propagation) neural network. The experimental results show that the features of the power spectrum can be extracted efficiently through this method, and the trained neural networks show high identification precision and the ability of extension.