原子能科学技术2009，Vol.43Issue(11)：1003-1008,6.
基于数据融合的核动力装置故障诊断方法
Nuclear Power Plants Fault Diagnosis Method Based on Data Fusion
谢春丽 1刘永阔 2夏虹2
作者信息
- 1. 东北林业大学,交通学院,黑龙江,哈尔滨,150040
- 2. 哈尔滨工程大学,核科学与技术学院,黑龙江,哈尔滨,150001
- 折叠
摘要
Abstract
The data fusion is a method suit for complex system fault diagnosis such as nuclear power plants, which is multisource information processing technology. This paper uses data fusion information hierarchical thinking and divides nuclear power plants fault diagnosis into three levels. Data level adopts data mining method to handle data and reduction attributes. Feature level uses three parallel neural networks to deal with attributes of data level reduction and the outputs of three networks are as the basic probability assignment of Dempster-Shafer (D-S) evidence theory. The improved D-S evidence theory synthesizes the outputs of neural networks in decision level, which conquer the traditional D-S evidence theory limitation which can't dispose conflict information. The diagnosis method was tested using correlation data of literature. The test results indicate that the data fusion diagnosis system can diagnose nuclear power plants faults accurately and the method has application value.关键词
核动力装置/故障诊断/数据融合Key words
nuclear power plant/ fault diagnosis/ data fusion分类
能源科技引用本文复制引用
谢春丽,刘永阔,夏虹..基于数据融合的核动力装置故障诊断方法[J].原子能科学技术,2009,43(11):1003-1008,6.
