基于神经模糊Petri网的高压断路器故障诊断研究

High Voltage Circuit Breaker Fault Diagnosis Based on Neural Fuzzy Petri Nets

为提高高压断路器运行的稳定性,该文借助Petri网的强大的知识表达和逻辑推理功能对高压断路器的状态进行评估和诊断。根据断路器的物理逻辑关系,构建了基于神经模糊Petri网的高压断路器故障诊断模型;采用失效模式与效应分析(FMEA)法对故障统计数据进行处理,求取库所置信度、变迁阈值、库所权值、规则可信度;优化正向推理算法,实现对高压断路器故障的准确预测;逆向推理结合最小割集可有效避免检修的盲目性。最后,以部分模型为例,进行推理分析,并通过故障树和统计数据来验证推理模型的正确性和合理性。

In order to improve the stability of high voltage circuit breaker, this paper evaluates and diagnoses the state of high voltage circuit breaker by Petri net theory, for its powerful knowledge expression and logic inference function. According to the logic relationship of the circuit breaker, a fault diagnosis model of high voltage circuit breaker based on Petri is constructed; The failure mode and effect analysis（FMEA） method is used to deal with the fault statistics, and the credibility of place, threshold of transition, weight of place and credibility of transition; Optimize the forward inference algorithm to achieve accurate prediction of high voltage circuit breaker failure; Inverse inference combined with the minimum cut set can effectively avoid the blindness of maintenance. Finally, the part of model is used to deduce and analyze, the correctness and rationality of the reasoning model are verified by the fault tree and the data of statistics.