Optimization Technique for Neural Network-Based Error Compensation in CNC Machining

Abstract:

The neural network (NN) is extensively used for error predication and compensation in CNC machining. However, the training samples are finite and have some noises which limit the training accuracy of the neural network. Furthermore, the weight matrixes and the valve values of the NN are fixed which limit the generalization performance of the trained NN. To solve the problems, some optimization techniques are proposed in this paper. A standardized formula is proposed to standardize the training samples. The data filter is designed to eliminate the noise. A correction strategy is proposed to realize the generalization performance of the trained NN.

• Periodical: Advanced Materials Research (Volumes 189-193)
• Pages: 1878-1881
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.189-193.1878
• Online since: February 2011
• Authors: Kai Guo Fan, Jian Guo Yang
• Keywords: Error Compensation, Neural Network (NN), Optimization

References

[1] C. Raksiri, M. Parnichkun: I.J. Machine Tools & Manufacture 44 (2004).

[2] Y. Kang, C.W. Chang, Y. Huang, C.L. Hsu: I.J. Machine Tools & Manufacture 47 (2007).

[3] J.M. Fines, A. Agah: Engineering Applications of Artificial Intelligence 21 (2008).

[4] M.A. Donmey: (1985).

[5] J.G. Yang: Error synthetic compensation technique and application for NC machine tools, Shanghai Jiaotong University, (1998).

[6] K.G. Fan, J.G. Yang: Submitted to I.J. Machine Tools & Manufacture (2010).

[7] R. Ramesh, M.A. Mannan, A.N. Poo: I.J. Machine Tools & Manufacture 40 (2000).

[8] K.G. Fan, J.G. Yang: Chinese Journal of Mechanical Engineering, Accepted July (2010).