基于改进D-S证据理论的燃气轮机滑油系统故障诊断

本文使用D-S证据理论决策层融合结构融合了4种经典信息融合算法,对滑油系统典型故障进行诊断。为解决证据冲突问题,本文对D-S证据理论公式进行了改进,并验证了改进公式在特征层和决策层的融合效果。结论表明本文提出的D-S证据理论改进方法能够较好地解决证据冲突带来的问题,可以提高诊断正确率;证据理论在决策层融合中的优势较为明显,应用于多种方法诊断结果的决策层融合可以提高诊断的容错性。

Gas Turbine Lubricating Oil System Fault Diagnosis Based on Improved D-S Evidence Theory

In this paper, D-S evidence theory decision-making fusion structure is used to fusion the results diagnosed by four classical information fusion algorithms for lubricating system fault. In order to solve the problem of evidence conflict, this paper improves the D-S evidence theory and verifies the fusion effect of the improved formula at the feature level and the decision level. The conclusion shows that the improved DS evidence theory proposed in this paper can solve the problems brought by evidence conflicts and improve the accuracy of diagnosis. Evidence theory has obvious advantages in decision level fusion.Using decision fusion structure to fusion diagnosis results of multiple methods can improve the fault tolerance.