基于改进粒子群优化T-S ANFIS算法的诊断油浸式变压器故障研究  

Research on Fault Diagnosis of Oil Immersed Transformer Based on Improved Particle Swarm Optimization T-S ANFIS Algorithm

作　　者：乐效鹏 史兵[1] 李嘉诚 YUE Xiaopeng;SHI Bing;LI Jiacheng(College of Mechanical and Rail Transportation,Changzhou University,Changzhou 213164,China)

机构地区：[1]常州大学机械与轨道交通学院,江苏常州213164

出　　处：《计算机测量与控制》2023年第10期33-39,共7页Computer Measurement &Control

基　　金：江苏省研究生实践创新计划项目(SJCX22_1414)。

摘　　要：为了有效提升油浸式变压器故障诊断的精度与速度,提出一种基于改进粒子群算法(IPSO)优化T-S型自适应模糊神经网络(T-S ANFIS)的油浸式变压器故障诊断模型;引入动态惯性权重和学习因子线性调整策略,并利用收敛域和欧式距离判别雷同粒子,以克服粒子群算法易早熟、后期易陷入局部最优的问题;接着通过IPSO对T-S ANFIS的前提参数进行优化,提高网络的收敛速度;最后通过仿真实验验证基于IPSO优化T-S ANFIS的变压器故障诊断模型效果,结果表明所构建模型的故障诊断最优准确率约为98%,与ANFIS及PSO-ANFIS模型相比具有较高的故障诊断精度及效率。In order to effectively improve the accuracy and efficiency of fault diagnosis for oil-immersed transformers,An oil-immersed transformer fault diagnosis model based on improved particle swarm optimization(IPSO)optimized T-S adaptive neuro fuzzy inference system(T-S ANFIS)is proposed.The dynamic inertia weight and linear learning factor adjustment strategy are introduced,the convergence domain and Euclidean distance are utilized to distinguish identical particles,and overcome the problems of premature convergence and local optima in particle swarm optimization.Furthermore,IPSO is used to optimize the T-S ANFIS's premise parameters and improve the network's convergence speed.Finally,through the simulation experiments,the effectiveness of the IPSO-optimized T-S ANFIS fault diagnosis model is verified,the results show the optimal fault diagnosis accuracy of the proposed model reaches about 98%,compared with ANFIS and PSO-ANFIS models,the proposed model has a high accuracy and efficiency in fault diagnosis.

关 键 词：油浸式变压器 改进粒子群 自适应模糊神经网络 故障诊断 算法优化 

分 类 号：TP806[自动化与计算机技术—检测技术与自动化装置]