Reliability Analysis of Automotive Rear-Axle Bumper by Using Adaptive Neural-Fuzzy Inference System

Abstract:

Adaptive neuro-fuzzy inference system[1] is an advanced algorithm to estimate important parameters based on limited available information. We conducted a specific analysis about this algorithm to validate our viewpoint compared with Weibull distribution[2], and rear-axle bumper was used for our experiment. The experimental results indicate that ANFIS can be more precise than Weibull distribution and more close to the real circumstances. According to the root mean square root that decreases to a relatively low value, we could infer that ANFIS is a good approach to estimate all data based on the limited given samples.

• Periodical: Key Engineering Materials (Volumes 474-476)
• Pages: 436-441
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.474-476.436
• Online since: April 2011
• Authors: Jia Wei Xu, Seop Hyeong Park, Xian Yun Fei
• Keywords: Adaptive Neural Fuzzy Inference System (ANFIS), Fuzzy Logic(FL), Membership Function, Weibull Distribution

References

[1] Pejman Tahmasebi, Ardeshir Hezarkhani, Application of Adaptive Neuro-Fuzzy Inference System for Grade Estimation. Australian Journal of Basic and Applied Sciences[J], Vol. 4No. 3, (2010), 408-420.

[2] Wang Dawei, Re liaility life time ana lysis of the turbine blade of turbofan engine, Journal of Beijing University of Aeronautics and Astronautics[J], Vol. 32　No18(In chinese), August (2006).

[3] Block, H.W. Continuous multivariate exponential extensions, Reliability and Fault Tree Analysis[J], SIAM, (1975) , 285-306.

[4] F. Cus, J. Balic, U. Zuperl, Hybrid ANFIS-ants system based optimisation of turning parameters, Achievements in Materials and Manufacturing Engineering [J], Vol36 No. 1September (2009).

[5] Richard O. Duda, Peter E. Hart, David G. Stork，Pattern Classification (2nd Edition) [M], (Wiley-Interscience, 2000).

[6] Cheng, Q. and F.P. Agterberg, Fuzzy weights of evidence and its application in mineral potential mapping: Natural Resources. Researche[J], Vol 8No. 1, (1999), 27-35.

[7] Information on www. nd. edu/~hpcc/solaris8_usr_local/src/matlab6. 1/help/toolbox/fuzzy/anfis. html.

[8] Yang Li, A new validity function for fuzzy clustering, Proceedings of International Conference on Computational Intelligence and Natural Computing, 2009, Wuhan, June 6-7, (2009), pp.462-465.

DOI: 10.1109/cinc.2009.100

[9] V. Vapnik, The Nature of Statistical Learning Theory[M]. (New York: Springer Verlag, 1995).