Application of Deep Learning Neural Network in Fault Diagnosis of Power Transformer

doi:10.3969/j.issn.1000-7229.2015.12.018

Abstract

Abstract:

As oil chromatography online-monitoring data is unlabeled during power transformer failure, project sites tend to get a large number of unlabeled fault samples. However, traditional diagnosis methods often fail to make full use of those unlabeled fault samples in judging transformer fault types. Based on deep learning neural network （DLNN）, a corresponding classification model was established, whose classification performance was analyzed and tested by typical datasets. On this basis, a new fault diagnosis method of power transformer was further proposed, in which a large number of unlabeled data from oil chromatogram on-line monitoring devices and a small number of labeled data from dissolved gas-in-oil analysis （DGA） were fully used in training process. It could generate fault diagnosis result in the form of probabilities, and provide more accurate information for the maintenance of power transformer because of its better performance in fault diagnosis. Testing results from engineering example indicate that the proposed method is correct and feasible, and its diagnosis performance is better than that of three radio, BP neural network and support vector machine, which is suitable for the fault diagnosis of power transformer.

Key words: power transformer, fault diagnosis, dissolved gas-in-oil analysis（DGA）, deep learning neural network（DLNN）

CLC Number:

TM 721

SHI Xin, ZHU Yongli. Application of Deep Learning Neural Network in Fault Diagnosis of Power Transformer[J]. ELECTRIC POWER CONSTRUCTION, 2015, 36(12): 116-122.

References

［1］ Tang W H，Wu Q H.Condition monitoring and assessment of power transformers using computational intelligence［M］.New York： Springer-Verlag Press，2011.
［2］朱德恒，严璋，谈克雄，等.电气设备状态监测与故障诊断技术［M］.北京：中国电力出版社，2009.
［３］王国平，余涛，傅森木，等.基于DGA的变压器故障诊断智能方法分析［J］.电力建设，2015，36（6）： 34-39.
Wang Guoping，Yu Tao，Fu Senmu，et al.Intelligent methods for transformer fault diagnosis based on DGA［J］.Electric Power Construction，2015，36（6）： 34-39.
［4］尹金良，朱永利，俞国勤，等.基于高斯过程分类器的变压器故障诊断［J］.电工技术学报，2013，28（1）：158-164.
Yin Jinliang，Zhu Yongli，Yu Guoqin，et al.Fault diagnosis of transformers based on Gaussian process classifier［J］.Transactions of China Electrotechnical Society，2013，28（1）： 158-164.
［5］王致杰，徐余法，刘三明，等.电力设备状态监测与故障诊断［M］.上海：上海交通大学出版社，2012.
［6］王涛，王晓霞.基于改进PSO-BP算法的变压器故障诊断［J］.中国电力，2009，42（5）： 13-16.
Wang Tao，Wang Xiaoxia.Power transformer fault diagnosis based on modified PSO-BP algorithm ［J］.Electric Power，2009，42（5）：13-16.
［7］周建华，胡敏强，周鹗.基于共轭梯度方向的CP-BP算法在变压器油中溶解气体诊断法中的应用［J］.中国电机工程学报，1999，19（3）：41-45.
Zhou Jianhua，Hu Minqiang，Zhou E.On the application of CP-BP algorithm for DGA-NN diagnosis in power transformer ［J］.Proceedings of the CSEE，1999，19（3）： 41-45.
［8］张艳，吴玲.基于支持向量机和交叉验证的变压器故障诊断［J］.中国电力，2012，45（11）：52-55.
Zhang Yan，Wu Ling.Transformer fault diagnosis based on C-SVC and cross-validation algorithm ［J］.Electric Power，2012，45（11）： 52-55.
［9］尹玉娟，王媚，张金江，等.一种自主核优化的二值粒子群优化-多核学习支持向量机变压器故障诊断方法［J］.电网技术，2012，36（7）：249-254.
Yin Yujuan，Wang Mei，Zhang Jinjiang，et al.An autonomic kernel optimization method to diagnose transformer faults by multi-kernel learning support vector classifier based on binary particle swarm optimization ［J］.Power System Technology，2012，36（7）：249-254.
［10］遇炳杰，朱永利.加权极限学习机在变压器故障诊断中的应用［J］.计算机工程与设计，2013，34（12）： 4340-4344.
Yu Bingjie，Zhu Yongli.Transformer fault diagnosis using weighted extreme learning machine ［J］.Computer Engineering and Design，2013，34（12）： 4340-4344.
［11］ Hinton G E，Salakhutdinov R R.Reducing the dimension-ality of data with neural networks［J］.Science，2006，313（5786）： 504-507.
［12］ Hinton G E，Osindero S，Teh Y W. A fast learning algorithm for deep belief nets［J］.Neural Computation，2006，18（7）： 1527–1554.
［13］ Bengio Y. Learning deep architectures for AI［J］.Foundations and Trends in Machine Learning，2009，2（1）： 1–127.
［14］ Bengio Y，Courville A，Bincent P.Unsupervised feature learning and deep learning： a review and new perspectives［R］.Montreal： Department of Computer Science and Operations Research，University of Montreal，2012.
［15］ Hinton G E. A practical guide to training restricted Boltzmann machines［R］.UMTL Tech Report 2010-003.Toronto，Canada： University of Toronto，2010.
［16］ Baker J，Deng L，Glass J，et al.Developments and directions in speech recognition and understanding，Part 1［J］.IEEE Signal Processing Magazine，2009，26（3）：75-80.
［17］ Yu D，Deng L.Deep learning and its applications to signal and information processing ［J］.IEEE Signal Processing Magazine，2011，28（1）：145-154.
［18］Zhang Lijing， Liang Yingli. A fast method of face detection in video images［C］// The 2nd IEEE International Conference on Advanced Computer Control （ICACC 2010）， Shenyang, China, 2010： 490-494.
［19］ Kalal Z，Mikolajczyk K，Matas J.Face-tld： Tracking-learning-detection applied to faces［C］//2010 International Conference on Image Processing （ICIP 2010），HongKong, China, 2010： 3789-3792.
［20］ Collobert R，Weston J.A unified architecture for natural language processing： deep neural networks with multitask learning［C］//Proceedings of the 25th International Conference on Machine Learning,2008： 160-167.
［21］余凯，贾磊，陈雨强，等. 深度学习的昨天、今天和明天［J］.计算机研究与发展，2013,50（9）:1799-1804.
Yu Kai, Jia Lei, Chen Yuqiang, et al. Deep learning: yesterday, today, and tomorrow［J］. Journal of Computer Research and Development, 2013, 50（9）:1799-1804.
［22］孙志军，薛磊，许阳明，等.深度学习研究综述［J］.计算机应用研究，2012，29（8）：2806-2809.
Sun Zhijun，Xue Lei，Xu Yangming，et al.Overview of deeplearning［J］.Application Research of Computers，2012，29（8）：2806-2809.
［23］ Andrew Ng.UFLDL Tutorial. http://openclassroom.stanford.edu/MainFolder/CoursePage.php?course=DeepLearning
［24］马勇，鲍长春，夏丙寅.基于辨别性深度信念网络的说话人分割［J］.清华大学学报：自然科学版，2013，53（6）： 804-807.
Ma Yong，Bao Changchun，Xia Bingyin.Speaker segmentation based on discriminative deep belief networks ［J］.Journal of Tsinghua University： Science and Technology，2013，53（6）： 804-807.
［25］孙劲光，蒋金叶，孟祥福，等. 一种数值属性的深度置信网络分类方法［J］.计算机工程与应用，2014, 50（2）: 112-115.
Sun Jinguang, Jiang Jinye, Meng Xiangfu, et al. DBN classification algorithm for numerical attribute ［J］. Computer Engineering and Applications, 2014, 50（2）: 112-115.
［26］王昌长，李福祺，高胜友.电力设备的在线监测与故障诊断［M］.北京：清华大学出版社，2006.

[1]	ZHENG TAO，ZHANG Zihang. Research on Internal Fault Diagnosis and Countermeasure of Modular Multilevel Converter Based on Half Bridge Sub-modules [J]. Electric Power Construction, 2018, 39(6): 42-.
[2]	ZHANG Yan, WEN Fushuan, XIONG Wen, NIU Zhenyong, ZHAO Hongwei, SHANG Huiyu . Wide Area Measurements Based Analytic Model for Power System Fault Diagnosis [J]. Electric Power Construction, 2018, 39(5): 10-.
[3]	ZHANG Yong1，LI Dan1，WEN Fushuan2，ZHANG Yan3，DONG Yi1，ZHENG Jianzi1. Process Level Fault Diagnosis in IEC 61850 Based Smart Substations [J]. Electric Power Construction, 2018, 39(3): 42-.
[4]	SHANG Huiyu, WANG Chongyu, CHEN Minghui, YANG Zeng, XIONG Wen, WEN Fushuan. A Feature Matching Based Method for Fault Diagnosis in Power Systems Under Disaster Weather [J]. Electric Power Construction, 2018, 39(10): 37-43.
[5]	WANG Shoupeng, ZHAO Dongmei . A Design Method for Power Grid Fault Diagnosis Model Based on Humoral Immunity Principle [J]. Electric Power Construction, 2017, 38(7): 131-.
[6]	XU Bing，ZHANG Yan，TIAN Fangyuan，WEN Fushuan，ZHU Bingquan，XU Lizhong. Fault Identification and Wide-Area Backup Protection Strategy Based on Limited Phasor Measurement Units [J]. Electric Power Construction, 2016, 37(2): 25-33.
[7]	LIAO Zhiwei，YUE Ling，WEN Fushuan，ZHU Bingquan，XU Lizhong. A Rule-Network Based Approach for Fault Diagnosis of HV Transmission Lines and Protection Action Performance Evaluation [J]. Electric Power Construction, 2016, 37(2): 34-41.
[8]	LEI Qian, JI Xingquan, WEN Fushuan, LIU Zhipeng, YU Yongjin, XU Huanqi. Fault Diagnosis of Distribution System with Distributed Generation Employing Transient Component [J]. Electric Power Construction, 2016, 37(2): 42-49.
[9]	CHEN Weibiao, CHEN Yiping, YAO Wei, SUN Yanbin, WEN Jinyu. A Fault Diagnosis Method of Power Grid Based on Time Series Matching with Multi-Source Information [J]. Electric Power Construction, 2016, 37(12): 134-.
[10]	HAN Zhonghe，JIAO Hongchao，ZHU Xiaoxun，WANG Zhi. SVM Rotor Vibration Fault Diagnosis Based on EEMD Permutation Entropy [J]. Electric Power Construction, 2016, 37(1): 92-96.
[11]	WANG Guoping， YU Tao，FU Senmu， ZHONG Yunping， ZHANG Yong， CHENG Xiaohua . Intelligent Methods for Transformer Fault Diagnosis Based on DGA [J]. ELECTRIC POWER CONSTRUCTION, 2015, 36(6): 34-39.
[12]	ZHU Tianyi, JIANG Tiezheng, LUO Jie, SONG Junying, XIE Xiaoqian. Fault Diagnosis Method of Transmission Lines Based on Electric Quantity Data [J]. ELECTRIC POWER CONSTRUCTION, 2014, 35(10): 74-78.
[13]	CHEN Yanqiao，ZHANG Fenfang. Optimization Design of Energy Saving for 330 MW Units Control Systems [J]. ELECTRIC POWER CONSTRUCTION, 2013, 34(1): 66-69.