Loader Boom Reliability Analysis with Artificial Neural Network Method

Abstract:

The artificial neural network is used to solve the reliability analysis of the engineering structure. When the limit state function of structure is highly complex or with nonlinearity, it is time-consuming or cumbersome to carry out reliability analysis with traditional methods. The artificial neural network response surface method is adopted to analyze the fatigue reliability of loader boom, the working process of loader machine is analyzed with FEM software and analytical method, the stress-time history and strain-time history of loader boom are schematized with rain-flow algorithm, consequently the fatigue life analysis on the structure can be carried out with local stress-strain method. The artificial neural network method is used to fit the performance function as well as its derivatives, so as to calculate the reliability of the structure. The numerical example results show that the proposed method has capability of solving industrial-scale reliability problems.

• Periodical: Advanced Materials Research (Volumes 838-841)
• Pages: 250-253
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.838-841.250
• Online since: November 2013
• Authors: Li Rong Sha*, Yue Yang
• Keywords: Artificial Neural Network (ANN), Fatigue, Reliability, Response Method

References

[1] Committee on fatigue and fracture reliability of the committee on structural safety and reliability of the structural division. Fatigue reliability 1–4. Journal of structural division, Proceedings of ASCE 108(ST1), (1982 ), p.3–88.

DOI: 10.1061/jsdeag.0005869

[2] L. Faravelli: A response surface approach for reliability analysis, Journal of Engineering Mechanics, Vol. 12 (1989 ), pp.2763-2781.

DOI: 10.1061/(asce)0733-9399(1989)115:12(2763)

[3] R. I. Stephens, A. Fatemi, R. R. Stephens, H. O. Fuchs: Metal Fatigue in Engineering, second ed. , John Wiley & Sons, Inc., New York, NY. (2001).

[4] A. Fatemi and L. Yangt: Cumulative fatigue damage and life prediction theories: a survey of the state of the art for homogeneous materials, International Journal of Fatigue , Vol. 1 (1998), pp.9-34.

DOI: 10.1016/s0142-1123(97)00081-9

[5] K. Hornik, M. Stinchcombe, H. White: Multi-layer feed-forward networks are universal approximators. Neural Networks. Vol. 2 (1989), p.359–368.

DOI: 10.1016/0893-6080(89)90020-8

[6] K. Hornik, M. Stinchcombe, H. White: Universal approximation of an unknown mapping and its derivatives using multi-layer feed-forward networks. Neural Networks. Vol. 3 (1990), p.551–560.

DOI: 10.1016/0893-6080(90)90005-6