基于模糊推理脉冲神经膜系统的变压器故障诊断方法

Transformer fault diagnosis method based on fuzzy inference pulse ueural membrane systems

油中溶解气体分析是目前变压器状态监测及故障诊断的主要手段,但气体含量易受到变压器容量、结构和故障工况等因素影响,存在一定程度的不确定性。因此,提出了一种基于模糊推理脉冲神经膜系统的变压器故障诊断方法。首先,根据油中溶解气体分析数据提取特征气体量值。其次,利用高斯型隶属函数对提取的特征气体量值进行模糊处理。在此基础上,根据故障类型所对应的模糊产生式规则,构建基于模糊推理脉冲神经膜系统的故障诊断模型。最后,利用模糊推理算法对故障诊断模型进行计算,得到每种故障类型的置信度,从而确定故障类型。实例分析结果表明,该方法能够有效地识别变压器各类型故障,具有较高的诊断正确率。

Dissolved gas analysis in oil is currently the main method of transformer state monitoring and fault diagnosis.Due to the concentrations of gases are easily affected by factors such as transformer capacity,structure,and fault conditions,gas analysis has a certain degree of uncertainty.To address this problem,a transformer fault diagnosis method based on fuzzy reasoning spiking neural p systems is proposed.Firstly,extract the characteristic gas value based on the data of the dissolved gas analysis in oil.Secondly,the Gaussian membership function is used to fuzzify the extracted characteristic gas value.By applying the fuzzy production rules from different fault type,a fault diagnosis model based on fuzzy reasoning spiking neural p systems is constructed.Finally,using the fuzzy reasoning algorithm to compute the confidence level of each fault type and indicate the fault diagnosis results.The case study shows that this method can effectively identify the different faults of transformer with high accuracy.