Error Compensation of a NC Machining System Based on a Dynamic Feedback Neural Network

Abstract:

Machining error of a NC machining system is a kind of comprehensive error in dynamically machining process; especially it is of errors with non-linear characteristics. In this paper, we will set up a kind of model of comprehensive errors analysis for a NC machining system and present an error compensation for high-precision a NC machining system by a dynamic feedback neural network embedded in a NC machine tool. The results obtained shows that this approach can effectively improve compensation precision and real time of error compensation on machine tools.

• Periodical: Applied Mechanics and Materials (Volumes 52-54)
• Pages: 1890-1894
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.52-54.1890
• Online since: March 2011
• Authors: Huang Lin Zeng, Yong Sun, Xiao Hong Ren, Li Xin Liu
• Keywords: Ant Colony Algorithm (ACA), Dynamic Feedback Neural Network, Principal Component Analysis (PCA), Rough Set Theory (RST)

References

[1] Huanglin Zeng , Yong Sun , Haiyan Zhang, Thermal Error Compensation on Machine Tools Using Rough Set Artificial Neural Networks, Proceeding of WRI World Congress on Computer Science an Information Engineering [C], Los Angeles, USA, (2009).

DOI: 10.1109/csie.2009.155

[2] Sun Yong, Huanglin Zeng, Tsang, A New Approach of Thermal Error Compensation on NC Machine Tools [J], (in Chinese), mechanical design and manufacturing, (2010), 2, pp.244-246.

[3] Zhao Hai-Tao, Thermal error measurement point layout and modeling of NC machine tool model analysis[D], (in Chinese), Shanghai: Shanghai Jiao Tong University, (2006) , pp.71-74.

[4] Yang Jianguo, Tang Weiguo, Ren Yonggiang, etc, machine thermal compensation of temperature variable packet optimization modeling [J], (in Chinese), Chinese mechanical engineering, (2004), 15 (6). pp.478-480.

[5] Huanglin Zeng, Intelligent Computing, Theoretical Aspects and Applications of Rough Sets [M], Fuzzy logic and Neutral Networks. (in Chinese), ChongQing Press, (2004), pp.1-60.

[6] Solnon, C.: Ants can solve constraint satisfaction problems [J]. IEEE Transactions on Evolutionary Computation, (2002), 6(4), p.347–357.

DOI: 10.1109/tevc.2002.802449

[7] Ke, L.J., Feng, Z.R. Ren, Z.G.: An efficient ant colony optimization approach to attribute reduction in rough set theory [J], Pattern Recognition Letters, (2008), 29(9), pp.1351-135.

DOI: 10.1016/j.patrec.2008.02.006

[8] Huanglin Zeng , Xiaohui Zeng, Reasoning Decision Rules of an Uncertain System, Proceeding of The Fourth International Conference on Rough Sets and Knowledge Technology[C]，Australia，Springer-Verlag Berlin Heidelberg, (2009), pp.634-642.

DOI: 10.1007/978-3-642-02962-2_80

[9] Haiyan Zhang, Huanglin Zeng, Tang Jian Fang, Optimization for Temperature Measurement Points of Compensating Thermal Error on Machine Tools Based on Rough Sets [J], (in Chinese), machine and hydraulic, (2010), 2, pp.39-41.

[10] Hu Hui, Zhang Biao, rough sets and principal component analysis based on neural network simulation circuit fault diagnosis [J], (in Chinese), automation and instrumentation, (2009), 3.