A Hybrid Model Using Genetic Algorithm and Neural Network for Optimizing Technology Parameters in Skew Rolling Seamless Pipes

Abstract:

In the production of seamless pipes, there are many factors influencing the quality of the seamless tubes such as diameter of original pipe, feed angle, temperature, minimum roll gap and so on. Unfortunately, the selection of the parameters still relies on manual operation and the experience of engineers. In this paper, a novel hybrid model through integration of genetic algorithm(GA) and neural network is proposed to optimize the technology parameters. Firstly, the neural network model is developed between technology parameters and final pipes dimensions. Then, genetic algorithm is used to optimize the neural network structure. At last, accuracy of the parameters is verified by experiment. The research results indicate that the proposed approach can effectively help engineers determine optimal technology parameters and achieve competitive advantages of product quality and costs

• Periodical: Advanced Materials Research (Volume 145)
• Pages: 117-122
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.145.117
• Online since: October 2010
• Authors: Jian Hua Hu, Yuan Hua Shuang, Peng Liu
• Keywords: Genetic Algorithm (GA), Neural Network (NN), Seamless Pipe, Skew Rolling

References

[1] USS Tubular products, http: /www. usstubular. com.

[2] Oh SI and S Kobayashi: International Journal of Mechanical Science, Vol. 17 (1975), p.293.

[3] Pham DT: Int J Mach Tools Manuf , Vol. 39(6), p.937.

[4] SH Huang and H Xing: Fuzzy Sets Syst Vol. 132(1999) No. 2, p.233.

[5] D. R. Hush and B. G. Horne: IEEE Signal Processing Magazine, (1993) No. l, p.8.

[6] H. -Y Tseng: J. Advanced Manufacturing Technology, Vol. 27(2006) No. 9, p.897.

[7] Y. C. Lam , Y. M. Deng and C. K. Au: Engineering with Computers, Vol. 21(2006) No. 3, p.193.

[8] C. -T. Su and H. -H. Chang: International Journal of Systems Science, Vol. 31(2000) No. 12, p.1543.

[9] S. -S. Han and G.S. May: Proceedings of 8th International Conference on Ttools with Artificial Intelligence(2006) p.200.

[10] H. Kurtaran, B. Ozcelik and T. Erzurumlu: Journal of Materials Processing Technology, Vol. 169(2005) No. 2, p.314.

[11] H. Dai and C. MacBeth: Neural Networks, Vol. 10(1997) No. 8, p.1505.

[12] G R Liu and X Han: Computational Inverse Techniques in Nondestructive Evaluation(CRC Press LLC, Florida, 2003).