Application of Differential Evolution Wavelet Neural Networks for State Recognition of Tool Wear

Abstract:

Tool wear monitor is one of the critical issue in industry, accurate prediction of tool life can guarantee surface quality, the new method of tool wear stated recognition was proposed with application of wavelet neural networks (WNN). An application of differential evolution (DE) algorithm was introduced to training artificial neural networks. The three layer wavelet neural network was constructed and optimized with differential evolution algorithm. Cutting force and cutting noise was monitored and the signal was processed as training samples for wavelet neural networks. Simulation with BPNN, WNN and DEWNN to show the new method can avoid normal neural networks with convergence quality and enhance learning speed, also the diagnosis precision and efficiency was improved.

• Periodical: Applied Mechanics and Materials (Volume 367)
• Pages: 457-461
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.367.457
• Online since: August 2013
• Authors: Xiao Yun Wang
• Keywords: Differential Evolution (DE), Simulation, State Recognition, Tool Wear, Wavelet Neural Network (WNN)

References

[1] M.C. Huang, Wave Parameters and Functions in Wavelet Analysis, Ocean Engineering, Vol. 31, No. 1, 2004, pp.111-125.

[2] Darnin E D. A Simple Procedure for Pruning Back-Propagation Trained Neural Networks, IEEE Trans. Neural Networks. 1990, 1(2). pp.239-242.

DOI: 10.1109/72.80236

[3] NOH Min-Seok, HONG Dae Sun, Implementation of remote monitoring system for prediction of tool wear and failure using ART2, Journal of Central South University of Technology (English Edition). 2011, 18(1). pp: 177-183.

DOI: 10.1007/s11771-011-0677-7

[4] F. F. Alonso and D. R. Salgado, analysis of the structure of vibration signals for tool wear detection, Mechanical Systems and Signal Processing, Vol. 22, No. 3, 2008, pp.259-267.

DOI: 10.1016/j.ymssp.2007.09.012

[5] R.J. Williams and D. Zipser,: A learning Algorithm for Cont- inually Running Fully Recurrent Neural Networks,: Neural Computation, Vol. 1, 1989, pp.270-280.

DOI: 10.1162/neco.1989.1.2.270

[6] Wang Wu, Su Liang-yu. Application of CMAC-PID Compound Control in PMLSM Servo System[J]. Advanced Materials Research Vols. 341-342(2012), pp.780-784.

DOI: 10.4028/www.scientific.net/amr.341-342.780

[7] Wang Wu, Wang Hong-ling, Bai Zheng-min. Fault Diagnosis of Three Level Inverter Based on Improved Neural Networks[J]. Lecture Notes in Electrical Engineering, 2011, Vol. 97, pp.55-62.

DOI: 10.1007/978-3-642-21697-8_8

[8] WU Yanliang, Ju Jiangang, Sun Youxian. An improved differential evolution for optimization of chemical process, CHINESE JOURNAL OF CHEMICAL ENGINEERING, 2008, (16)2, pp.228-234.

DOI: 10.1016/s1004-9541(08)60068-3

[9] YE XU, LING WANG. Differential evolution algorithm for hybrid flow-shop scheduling problems, JOURNAL OF SYSTEMS ENGINEERING AND ELECTRONICS. 22(5). pp.794-798.

DOI: 10.3969/j.issn.1004-4132.2011.05.011

[10] Y. Xu, L. Wang, L. P. Li. An effective hybrid algorithm based on simplex search and differential evolution for global optimization. Lecture Notes in Artificial Intelligence, 2009, 5755, pp.341-350.

DOI: 10.1007/978-3-642-04020-7_36

[11] WANG WU. Adaptive neuro sliding mode control for inverted pendulum. 2010 2nd Internation Conference on Computer Engineering and Technology (ICCET2010), 2010, VOL 1, pp.135-138.

DOI: 10.1109/iccet.2010.5486253

[12] Wang Wu, Wang Hong-ling, Bai Zheng-min. Fault Diagnosis of Three Level Inverter Based on Improved Neural Networks[J]. Lecture Notes in Electrical Engineering, 2011, Vol. 97, pp.55-62.

DOI: 10.1007/978-3-642-21697-8_8