论文部分内容阅读
为了在断路器故障时能快速、准确地找出故障原因,提出了一种基于粗糙集理论和贝叶斯网络的高压SF6断路器故障诊断的方法。该方法首先根据断路器的故障样本集找出征兆集合和故障集合之间的关系以建立断路器故障诊断决策表,然后利用粗糙集理论属性约简中的区分矩阵算法对决策表进行约简,剔除冗余知识,简化专家知识得到最小诊断规则进而构建贝叶斯网络可以有效降低网络结构的复杂性,最后利用贝叶斯网络的概率推理实现了对断路器故障原因的快速分析。经过实例证明,该方法用于高压SF6断路器的故障诊断是可行有效的,并且最后给出的结果还可以为断路器的状态检修提供依据。
In order to find out the cause of the fault quickly and accurately in the case of circuit breaker fault, a method of fault diagnosis of high voltage SF6 circuit breaker based on rough set theory and Bayesian network is proposed. Firstly, the relationship between the set of signs and the set of faults is found out according to the fault sample set of circuit breakers to establish the fault diagnosis decision list of the circuit breaker. Then, the decision matrix is reduced by using the discernibility matrix algorithm in attribute reduction of rough set theory. Eliminating the redundant knowledge, simplifying the expert knowledge to get the minimum diagnosis rules and constructing the Bayesian network can effectively reduce the complexity of the network structure. Finally, the probabilistic reasoning of the Bayesian network is used to realize the rapid analysis of the fault cause of the circuit breaker. The example proves that the method is feasible and effective for the fault diagnosis of high voltage SF6 circuit breaker, and the final result can also provide the basis for the condition maintenance of the circuit breaker.