A study on maintenance reliability allocation of urban transit brake system using hybrid neuro-genetic technique |
| |
Authors: | Chul-Ho Bae Yul Chu Hyun-Jun Kim Jung-Hwan Lee Myung-Won Suh |
| |
Affiliation: | 1.School of Mechanical Engineering,Sunkyunkwan University,Suwon,Korea;2.School of Electric & Computer Engineering,Mississippi State University,USA |
| |
Abstract: | For reasonable establishing of maintenance strategies, safety security and cost limitation must be considered at the same
time. In this paper, the concept of system reliability introduces and optimizes as the key of reasonable maintenance strategies.
This study aims at optimizing component’s reliability that satisfies the target reliability of brake system in the urban transit.
First of all, constructed reliability evaluation system is used to predict and analyze reliability. This data is used for
the optimization. To identify component reliability in a system, a method is presented in this paper which uses hybrid neuro-genetic
technique. Feed-forward multi-layer neural networks trained by back propagation are used to find out the relationship between
component reliability (input) and system reliability (output) of a structural system. The inverse problem can be formulated
by using neural network. Genetic algorithm is used to find the minimum square error. Finally, this paper presents reasonable
maintenance cycle of urban transit brake system by using optimal system reliability. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|