A Study on Optimization of Automotive Suspension Base on PSO-BP Network Algorithm

Abstract:

A BP neural network algorithm which bases on the particle swarm optimization（PSO） is advanced in this paper, Thus formed the PSO-BP network algorithm. It makes use of PSO to reach the global optimization of BP neural network’s weight value and threshold value，and the optimized BP network is used to optimize the automotive suspension. Simulation results shows that this algorithm can improve the weak points of the BP learning algorithm such as the slow convergence rate and the poor global covergence. It can also reduce the number of training and the error obviously.

• Periodical: Applied Mechanics and Materials (Volumes 121-126)
• Pages: 3760-3764
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.121-126.3760
• Online since: October 2011
• Authors: Chang Song Jiang, You De Li, Zhong Dong Wang
• Keywords: Automotive Suspension, BP Neural Network (BPNN), Parameter Optimization, Particle Swarm Optimization Algorithm (PSO), PSO-BP Algorithm

References

[1] Kennedy J, EberhartR C. Particle swarm optimization[A]. Proceedings of IEEE International Conference on Neutral Networks [C]. Australia: IEEE, 1995, 1942-(1948).

[2] SHIY. EBERHART R A modified particle swarm optimizer[C]. Proc IEEE Int Conf on Evolutionary Computation, Anchorage, (1998).

[3] Zhong Luo, Rao Wen-bi, Zou Cheng-ming. Artificial Neural Network and Its Fusion Application Technology [M]. Beijing: Science Press, (2007).

[4] Liu Hong-bo, Wang Xiu-kun, Meng Jun. Study on Neural Network Learning Based on Particle Swarm Optimization Algorithm [J]. Mini-Micro Systems, 2005，26(4): 638-640.

[5] Jiang Zheng-feng, Gao Jin-hua. The Characteristics, Application and Development of Neural Network Adaptive Control System [J]. Journal of Wuhan University of Technology, 2006, 28(4): 17-21.