Affiliation:
1. School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049, P. R. China
Abstract
In this paper, a rail crack examination method based on an optimized complex evolutionary algorithm is proposed. The proposed approach has overcome the problems in which the fault diagnosis of wavelet packet decomposition is easily influenced by environmental factors, and the traditional genetic algorithm has a slow convergence speed and is prone to prematurity. In current method, to control the convergence performance, the diversity probability Pg is added in the update operation. According to the characteristics of rail crack fault signal, optimization function and cost function which consider the information in time and frequency domains are constructed and the information extraction is effectively realized. From field testing, the obtained results demonstrate that the present crack fault examination algorithm has higher accuracy rate, faster convergence rate and good stability. The present research work not only make up for the deficiency of traditional algorithm, but also provides a new examination method for wheel and rail noise fault diagnosis.
Publisher
World Scientific Pub Co Pte Lt
Subject
Mechanical Engineering,Mechanics of Materials,General Materials Science
Reference18 articles.
1. Diameter of the World-Wide Web
2. Z. Bing, Research and Realization of Wheel-Rail Noise Feature Detection Algorithm (Xi'an Jiaotong University, 2011) pp. 30–39.
3. On the Convergent Evolution of Animal Toxins
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献