Prediction of Hardenability of Gear Steel Using Stepwise Polynomial Regression and Artificial Neural Network

Abstract:

The prediction of the hardenability of gear steel has been carried using stepwise polynomial regression and artificial neural networks (ANN). The software was programmed to quantitatively predict the hardenability of gear steel by its chemical composition using two calculating models respectively. The prediction results using artificial neural networks have more precise than the stepwise polynomial regression model. The predicted values of the ANN coincide well with the actual data. So an important foundation has been laid for prediction and controlling the production of gear steel.

• Periodical: Advanced Materials Research (Volumes 118-120)
• Pages: 332-335
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.118-120.332
• Online since: June 2010
• Authors: Xiu Hua Gao, Tian Yong Deng, Hao Ran Wang, Chun Lin Qiu, Ke Min Qi, Ping Zhou
• Keywords: BP, Hardenability, Neural Network (NN), Stepwise Polynomial Regression

References

[1] Q P Yang, J Zhang: Automobile Technology and Material Vol. 6 (1997), p.1.

[2] REN Yuanhe: Steel MakingVol. 11 (1995), p.16.

[3] ZUO Xiurong , JIANG Maofa, XUE Xiangyin: Steel Making Vol. 17 (2001), p.18.

[4] YU Qingbo, LIU Xianghua: Journal of Iron and Steel Research Vol. 14(2002), p.1.

[5] ZHANG Shiyu: Journal of Beijing Union University Vol. 10(1996), p.25.

[6] WANG Xu, WANG Hong, Wang Wen-hui: Application and Theory of Artificial Neural Networks (Press of Northeastern University Press, Shenyang , 2000).

[7] X.C. Li,W.X. Zhu D.S. Mei: Metallurgical Sinica Vol. 16 (2003), p.534.

[8] L. Rawtani, J.L. Rana and A.K. Tiwari: Computational Materials Science Vol. 15(1999), p.493.

[9] E.M. Moser, C.H. Faller and F. Eggimann: Thin Solid Films, Vol. 49 (1999),P. 355.