Tool Wear State Diagnosis Based on Wavelet Analysis-BP Neural Network

Abstract:

Cutting force collected by experiment is transformed by continue wavelet in order to overcome the disadvantage that signal processing analyzes single variable. The eigenvector which can reflect tool wear state is extracted from scale-energy matrix based on analysis, and BP neural network is established to predict tool wear. Trained network is used for prediction by unknown sample. Results show that this method can identify and diagnose accurately tool wear state.

• Periodical: Key Engineering Materials (Volumes 431-432)
• Pages: 253-256
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.431-432.253
• Online since: March 2010
• Authors: Ning Fan, Hang Liang, Pei Quan Guo
• Keywords: BP Neural Network (BPNN), Cutting Force, Diagnosis of Failures, Tool Wear, Wavelet Analysis

References

[1] C. K. Toh: Materials & Design, Vol. 2 (2004), pp.41-50.

[2] H. Liang, N. Fan and Z.H. Gao: Modular Machine Tool & Automatic Manufacturing Technique, Vol. 8 (2008), pp.46-49 (in Chinese).

[3] S. Mallat: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 2 (1989), pp.674-693.

[4] J. Chae and S.S. Park: International Journal of Machine Tools and Manufacture, Vol. 9 (2007), pp.1433-1441.

[5] S.J. Kim, H.U. Lee and D.W. Cho: International Journal of Machine Tools and Manufacture, Vol. 10 (2007), pp.1827-1838.

[6] S. Yaldız, F. Ünsaçar, H. Sağlam and et al: Mechanical Systems and Signal Processing, Vol. 4 (2007), pp.785-792.