基于D-S证据理论信息融合的故障诊断方法

Fault Diagnosis Method Based on D-S Evidence Theory Information Fusion

对证据推理理论用于故障诊断识别进行了论述和仿真。介绍了证据理论的相关重要概念,给出了一种常用构造基本概率赋值函数的方法以及分类规则的选取。应用D-S证据理论方法对系统进行故障分析,首先要解决的问题是要分析系统识别框架和故障特征向量的构造。以航空电源某故障为例,进行了诊断识别仿真和对比实验,验证了证据推理用于故障诊断的可行性。仿真结果表明,将证据推理方法应用于航空电源状态监测和故障诊断中,可大幅度提高故障诊断的准确性和置信度。

The application of D-S evidence theory in fault diagnosis and fault recognition were discussed and simulated. Interrelated conceptions of evidence theory were introduced, and a method of constructing basic probability evaluation function and selecting classification rule was presented. By use of D-S evidence theory method, the system fault was analyzed. The problem to be solved firstly was to analyze system recognition frame and construction of fault feature vector. Taking a fault of aviation power supply system as an example, the diagnosis, simulation, contrast and recognition experiments were performed, and the feasibility of application of D-S evidence theory in fault diagnosis was verified. The simulation results indicated that this method can be used in state monitor and fault diagnosis of aviation power supply system, and it can greatly improve accuracy, credibility, and reliability of fault diagnosis.