基于遗传神经网络与信息融合的实时智能故障诊断系统研究  

Study on Real-Time Intelligent Fault Diagnosis System Based on Genetic NN and Information Fusion

作　　者：蔡猛[1] 张大发[1] 张宇声[1] 金仁喜[2] 陈登科[1] 

机构地区：[1]海军工程大学船舶与动力学院,武汉430033 [2]海军潜艇学院,山东青岛266000

出　　处：《船海工程》2010年第5期173-176,180,共5页Ship & Ocean Engineering

摘　　要：在传统BP神经网络的基础上引入聚类分析方法与遗传优化算法,可有效降低BP神经网络的训练难度并提高其训练精度;为有效利用各诊断单元的诊断结果,引入D-S证据理论对结论进行决策分析。仿真测试表明,该故障诊断系统能迅速、准确、可靠的诊断出各种故障。The method of clustering analysis and algorithm of genetic optimization was introduced to traditional BP neural-network to reduce training difficulty of BP neural-network and increase training precision.The D-S evidence theory was used to analyze conclusions in order to utilize diagnosis result of each diagnosis cell effectively.The simulation test validated that this fault diagnosis system can diagnose fault rapidly,exactly and reliably.

关 键 词：故障诊断 神经网络 遗传算法 聚类分析 信息融合 

分 类 号：U674.761[交通运输工程—船舶及航道工程] TL383[交通运输工程—船舶与海洋工程]