中国机械工程Issue(10)：1341-1345,5.DOI:10.3969/j.issn.1004-132X.2014.10.013
基于改进证据理论的多传感器信息融合故障诊断
Multi-sensor Information Fusion Fault Diagnosis Based on Improved Evidence Theory
摘要
Abstract
Aiming at conflict evidence resulting from uncertainty of sensor signals,a new multi-sensor information fusion fault diagnosis approach was proposed based on improved evidence theory. Firstly,a method to create original evidence was put forward using genetic neural network,where ge-netic algorithm was used to optimize neural network parameters so as to enhance the training speed. Secondly,vector space and direction similarity were defined and classification rule function was built to distinguish conflict evidence and similar evidence.Credibility modified conflict evidence to decrease the conflict effect from uncertainty.Finally,gear pump fault tests prove the validity of improved method, whose diagnosis precision is higher than that of single sensor diagnosis evidently.The threshold setup increases the flexibility and applicability.关键词
证据理论/遗传神经网络/冲突证据/故障诊断Key words
evidence theory/genetic neural network/conflicting evidence/fault diagnosis分类
信息技术与安全科学引用本文复制引用
刘希亮,陈桂明,李方溪,张倩..基于改进证据理论的多传感器信息融合故障诊断[J].中国机械工程,2014,(10):1341-1345,5.基金项目
国防预研基金资助项目(9140A27020309JB4701) （9140A27020309JB4701）
