基于IPSO-BP神经网络的变压器故障诊断方法①.PDFVIP

2013 年 第 22 卷 第 4 期 计 算 机 系 统 应 用 基于IPSO-BP 神经网络的变压器故障诊断方法① 1 2 3 张 锐 , 韩 超 , 李晓娜 1(吉林省电科院, 长春 130021) 2(东北电力大学 自动化工程学院, 吉林 132012) 3(东北电力大学 电气工程学院, 吉林 132012) 摘 要: 标准粒子群优化(PSO)算法对惯性权重采取简单的线性衰减方案, 无法获得全局最优点. 为了弥补该方 法的缺陷, 提出了一种改进的粒子群优化(IPSO)算法, 并将该算法与误差反向传播神经网络(BPNN)相结合, 进而 提出一种基于 IPSO-BPNN 的变压器故障诊断新方法. 该方法将单个粒子连续被选为最优解的次数作为自适应变 量, 并根据粒子的性能分类结果, 自适应地调整各粒子的惯性权重, 从而达到平衡局部和全局搜索能力的目的. 大量仿真表明该算法性能明显优于基于 BPNN 和 PSO-BPNN 的变压器故障诊断系统, 变压器故障诊断正确率更 高. 关键词: 变压器; 故障诊断; BPNN; PSO 算法; IPSO 算法 Transformer Fault Diagnosis Method Based on IPSO-BP Neural Network 1 2 3 ZHANG Rui , HAN Chao , LI Xiao-Na 1(Jilin Electric Power Research Institute, Changchun 130021, China) 2(School of Automation Engineering, Northeast Dianli University, Jilin 132012, China) 3(School of Electrical Engineering, Northeast Dianli University, Jilin 132012, China) Abstract: Standard particle swarm optimization (PSO) algorithm just takes simple linear attenuation way to update the inertia weight, so it can not get the global optimum value. In order to solve this problem, in the paper, an improved particle swarm optimization (IPSO) algorithm is proposed, which is combined with the error back propagation neural network (BPNN), then a new transformer fault diagnosis method based on IPSO-BPNN is presented. The method gets the number of times for which the individual particle is continuously selected as the optimal point, which is taken as an adaptive variable and is used to adaptively adjust the inertia weight along with the particle’s performance classification, so as to balance the local and global search capabilities. A large number of simulation shows that the algorithm is better than the BPNN and PSO-BPNN ba