基于并行化BP神经网络的配电变压器故障快速诊断方法A Fast Fault Diagnosis Method of Distribution Transformer Based on Parallel BP Neural Network
赵志新,赵宗罗,赵颖,王子凌,俞建飞,李忠民
ZHAO Zhixin,ZHAO Zongluo,ZHAO Ying,WANG Ziling,YU Jianfei,LI Zhongmin
摘要(Abstract)：
为进一步提升电网设备运行可靠性,提出一种基于MapReduce并行化的BP神经网络算法——MR-BPNN算法,以实现配电变压器故障快速诊断。该方法基于Hadoop平台下的MapReduce并行化模块:首先采用Map过程,运用不同训练样本块对各计算节点BP神经网络进行训练;然后采用Reduce过程,利用Map过程输出对BP神经网络权值进行汇总更新。相较于传统BP神经网络算法,MR-BPNN算法的网络训练收敛速度明显加快。最后,基于所采集的某电力公司配电变压器油中溶解气体数据,对比采用所提方法与传统特征气体法、三比值法进行设备故障诊断的性能,验证了所提方法可实现配电变压器状态的快速识别与诊断。
In order to improve the operation reliability of power grid equipment, a parallel MapReduce-based BP neural network method(MR-BPNN) is proposed for fast fault diagnosis of distribution transformers. The method is constructed based on the MapReduce parallel module under Hadoop platform. Firstly, the BP neural network of each calculation node is trained by using different training sample blocks in Map process, and then the weight of BP neural network is summarized and updated by Map process output. Compared with the traditional BP neural network algorithm, the convergence rate of MR-BPNN network training is increased obviously. Finally, the performance of the proposed method in equipment fault diagnosis is compared with the traditional characteristic gas method and three ratio method. It is proved that the proposed method can realize the rapid identification and diagnosis of the distribution transformer state.
关键词(KeyWords)：
状态检修;配电变压器;故障诊断;神经网络
condition-based maintenance;distribution transformer;fault diagnosis;neural network
基金项目(Foundation): 国网浙江省电力有限公司科技项目（5211DS20008H）
作者(Author):
赵志新,赵宗罗,赵颖,王子凌,俞建飞,李忠民
ZHAO Zhixin,ZHAO Zongluo,ZHAO Ying,WANG Ziling,YU Jianfei,LI Zhongmin
DOI: 10.19585/j.zjdl.202112011
参考文献(References)：
- [1]刘以刚.配电变压器绕组故障在线诊断方法研究[D].重庆：重庆大学，2014.
- [2]方鑫，殷俊，蒋苏，等.基于等距K-means和apriori算法的配电网故障规律挖掘方法[J].智慧电力，2020,48(10):99-104.
- [3]聂光辉.关于《配电网建设改造行动计划》的几点思考[J].中国电力企业管理，2016(13):22-24.
- [4]王健一，李金忠，凌愍，等.新版电力行业标准《变压器油中溶解气体分析判断导则》解读[J].变压器，2014,51(12):49-53.
- [5]ILLIAS H A,CHAI X R,ABU BAKAR A H.Hybrid modified evolutionary particle swarm optimisation-time varying acceleration coefficient-artificial neural network for power transformer fault diagnosis[J].Measurement,2016,90:94-102.
- [6]EQUBAL M D,KHAN S A,ISLAM T.Transformer incipient fault diagnosis on the basis of energy-weighted DGA using an artificial neural network[J].Turkish Journal of Electrical Engineering&Computer Sciences,2018,26:77-88.
- [7]YANG X H,CHEN W K,LI A Y,et al.BA-PNN-based methods for power transformer fault diagnosis[J].Advanced Engineering Informatics,2019,39:178-185.
- [8]LI J Z,ZHANG Q G,WANG K,et al.Optimal dissolved gas ratios selected by genetic algorithm for power transformer fault diagnosis based on support vector machine[J].IEEE Transactions on Dielectrics and Electrical Insulation,2016,23(2):1198-1206.
- [9]ZENG B,GUO J,ZHU W Q,et al.A transformer fault diagnosis model based on hybrid grey wolf optimizer and LS-SVM[J].Energies,2019,12(21):4170.
- [10]KARI T,GAO W S,ZHAO D B,et al.Hybrid feature selection approach for power transformer fault diagnosis based on support vector machine and genetic algorithm[J].IET Generation,Transmission&Distribution,2018,12(21):5672-5680.
- [11]YUAN F,GUO J,XIAO Z H,et al.A transformer fault diagnosis model based on chemical reaction optimization and twin support vector machine[J].Energies,2019,12(5):960.
- [12]郭栋，熊文真，徐建新，等.基于变精度粗糙集与量子贝叶斯网络的变压器故障诊断研究[J].计算机应用与软件，2017,34(2):93-99.
- [13]仝兆景，秦紫霓，赵运星，等.基于贝叶斯网络的变压器故障诊断研究[J].电子科技，2021,34(3):43-47.
- [14]XIAO Y,PAN W G,GUO X M,et al.Fault diagnosis of traction transformer based on Bayesian network[J].Energies,2020,13(18):4966.
- [15]LIN S,CHEN X Y,WANG Q.Fault diagnosis model based on Bayesian network considering information uncertainty and its application in traction power supply system[J].IEEE Transactions on Electrical and Electronic Engineering,2018,13(5):671-680.
- [16]AGRAWAL R.Integrated parallel K-nearest neighbor algorithm[C]//Smart Intelligent Computing and Applications.[S.l.]:[s.n.],2019:479-486.
- [17]刘畅，吴艳娟，高雅琦.基于BP神经网络及蜂群算法的变压器故障诊断[J].新型工业化，2020,10(4):7-12.
- [18]王峰，毕建刚，万梓聪，等.基于深度卷积神经网络的变压器故障诊断方法[J].广东电力，2019,32(9):177-183.
- [19]刘文泽，张俊，邓焱.基于深度置信网络和多维信息融合的变压器故障诊断方法[J].电力工程技术，2019,38(6):16-23.
- [20]杨玥，康琪.基于动态贝叶斯网络的变压器运行状态实时监测[J].内蒙古电力技术，2019,37(3):7-11.
- [21]陈如意，江军，陈珉，等.基于最大信息系数的变压器过热故障特征选择[J].电力工程技术，2020,39(2):140-145.
- [22]贾新民，蔡文超，贾俊青.多起同型号配电变压器故障分析及处理[J].内蒙古电力技术，2020,38(6):74-76.
- [23]李君，杨凯歌，谢佳成，等.油纸复合套管受潮状态的频域介电响应分析[J].电网与清洁能源，2020,36(11):1-7.
- [24]袁国刚，饶柱石.基于振动分析法的变压器非电量状态监测与诊断研究[J].发电技术，2019,40(2):134-140.
- [25]陈雪敏，焦雪松，曹浩.基于BP神经网络的城市排水系统节能算法优化研究[J].浙江水利水电学院学报，2020,32(5):27-30.
- [26]李文萱，殷大澍，刘倩.基于扰动观测器和神经网络的自动门系统安全性优化研究[J].浙江水利水电学院学报，2020,32(6):64-68.