Forecasting of the Fatigue Life of Metal Weld Joints Based on Combined Genetic Neural Network

Abstract:

For metal weld joints, due to the complex non-linear relationship among the factors which influence the fatigue performance, so it is hard to establish an accurate theoretical model to forecast its fatigue life. Based on the self-learning ability and approximation of non-linear mapping capability of the artificial neural network (ANN) and the powerful ability of global optimization of the genetic algorithm (GA), the paper through optimizing the ANN by GA, establishes combined genetic neural network (GA–ANN). The method establishes the mapping relationship between the fatigue life of metal weld joints and a variety of influencing factors, having greatly increased the computational efficiency for the fatigue life of metal weld joints, also had a higher forecast accuracy. The superiority of this method had been tested by the forecast of the fatigue life of weld joints in different process parameters, the new method to forecast the fatigue life of metal weld joints is proposed.

• Periodical: Key Engineering Materials (Volumes 439-440)
• Pages: 195-201
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.439-440.195
• Online since: June 2010
• Authors: Dan Ma, Zhan Qing Chen, Xian Lei Shan
• Keywords: Combined Genetic Neural Network (GA–ANN), Fatigue Life, Forecast Accuracy, Weld Joint

References

[1] T. Zhu, F. Gao and G. Liu: Pre-estimation of fatigue life time of welding spots of BIWs (Chinese). Automobile Technology. Vol. 2 (2006), pp.37-39.

[2] A. Jia, X. Jiang, G. Hui, H. Yao and X. Xi: Artificial neural network prediction of the microstructure of 60Si2MnA rod based on its controlled rolling and cooling process parameters. Mater. Sci. Eng. Vol. A344 (2003), pp.318-322.

DOI: 10.1016/s0921-5093(02)00444-6

[3] N.S. Reddy, A.K. Prasada Rao, M. Chakraborty and B.S. Murty: Prediction of grain size of Al-7Si Alloy by neural networks. Mater. Sci. Eng. Vol. A391 (2005), pp.131-140.

DOI: 10.1016/j.msea.2004.08.042

[4] Ó. Martín, M. López, P.D. Tiedra and M.S. Juan: Prediction of magnetic interference from resistance spot welding processes on implantable cardioverter-defibrillators. Journal of Materials processing technology. Vol. 206 (2008), pp.256-262.

DOI: 10.1016/j.jmatprotec.2007.12.021

[5] C. Liang and X. Liu: Strength prediction of sheet to tube single sided resistance spot welding, Materials and Design Vol. 30 (2009), pp.4328-4334.

DOI: 10.1016/j.matdes.2009.04.015

[6] X. Wang, C. Xu, J. Zhang, S. Li and Y. Niu: Fatigue life prediction of friction stir welding joints of aluminum alloy 707027651 based on BP algorithm of neural network (Chinese), Journal of Lanzhou University of Technology. Vol. 34 (2008).

[7] D. Yan, D. Zhou, C. Huang and Z. Wu: Modeling and predicting of LCCC solder Joint 3-D shape by minimum potential energy theory (Chinese), Journal of Guilin University of Technology. Vol. 26 (2006), pp.107-110.

[8] S. Pal, S. K. Pal and A. K. Samantaray: Artificial neural network modeling of weld joint strength prediction of a pulsed metal inert gas welding process using arc signals, Journal of Materials processing technology. Vol. 202 (2008), pp.464-474.

DOI: 10.1016/j.jmatprotec.2007.09.039

[9] L. Di, T. Srikanthan, R.S. Chandel and I. Katsunori: Neural-network based self-organized fuzzy logic control for arc welding. Engineering Application of Artificial Intelligence. Vol. 14 (2001), pp.115-124.

DOI: 10.1016/s0952-1976(00)00057-9

[10] Ó. Martín, M. López and F. Martín: Artificial neural networks for quality control by ultrasonic testing in resistance spot welding, Journal of Materials processing technology. Vol. 183 (2007), pp.226-233.

DOI: 10.1016/j.jmatprotec.2006.10.011

[11] F. Chen: Genetic algorithms and artificial neural network-Training artificial neural network by EGA-GDR. Journal of Chemical Industry and Engineering. Vol. 47 (1996), pp.280-286.

[12] Y. Zhong and B. Wang: BP network sequence prediction model based on genetic algorithm (Chinese). Systems Engineering and Electronics. Vol. 24 (2002), pp.9-11.

[13] X. Xue, W. Zhang and H. Liu: Estimation of bearing capacity of bolts on genetic neural network (Chinese), Journal of Engineering Geology. Vol. 14 (2006), pp.249-252.

[14] L. Wei, W. Xu, Z. Jiang S. Liu and J. Chen: Application of genetic neural network method to forecasting horizontal deformation of support structure at foundation pit (Chinese). Journal of Engineering Geology. Vol. 11 (2003), pp.297-301.

[15] G.F. Miller, P.M. Todd and S.U. Hedge: Designing neural networks using genetic algorithms. In: Proceedings of Third International Conference on Genetic Algorithms, (1989), pp.379-384.

[16] J.H. Holland: Adaptation in �atural and Artificial Systems. Ann Arbor, MI: University of Michigan Press, (1975).

[17] D.E. Goldberg: Genetic Algorithm in Search, Optimization, and Machine Learning. New York: Addison - Wesley, (1989).

[18] B. Arafehl, A.C. Singhh and M. Putatundask: A neural fuzzy logic approach to material processing. IEEE Transactions on Systems, Man, and Cybernetics Part C: Applications and Reviews. Vol. 29 (1999), pp.362-370.

DOI: 10.1109/5326.777072

[19] L.K. Charles, Y. lgor and N. Keith: Solving inverse initial-value boundary-value problems via genetic algorithm. Engineering Application of Artificial Intelligence. Vol. 13 (2000), pp.625-633.

DOI: 10.1016/s0952-1976(00)00025-7

[20] X. Zhao, L. Zhang and J. Fan: Prediction of wear trend using combined BP neural network based on genetic algorithm (Chinese), Lubrication Engineering. Vol. 9 (2005), pp.40-42.