刘云鹏;许自强;和家慧;王权;高树国;赵军;

• 1:河北省输变电设备安全防御重点实验室(华北电力大学)
• 2:新能源电力系统国家重点实验室(华北电力大学)
• 3:国网河北省电力有限公司电力科学研究院

摘要(Abstract)：

数据非均衡问题是制约机器学习技术在电力变压器故障诊断领域中应用效果的关键因素。为克服传统过采样方法未考虑数据整体分布信息的缺陷,提出了一种基于深度学习的故障数据增强方法,以实现样本库的类别均衡化目标。首先,建立梯度惩罚优化的条件式Wasserstein生成对抗网络模型以指导多类别故障样本的生成过程,并克服了原始生成对抗网络模型的训练不稳定问题;然后,构建以油中溶解气体无编码比值为特征参量的栈式自编码器诊断模型,并进一步提出了基于数据增强方法的设备故障诊断技术框架;最后,选用由准确率、F1度量以及G-mean组成的评价指标体系对类别均衡化前后的模型诊断效果进行评估对比。算例研究结果表明,相较于传统过采样方法,提出的故障样本增强方法能够更为有效地改善诊断模型对于多数类的分类偏好问题,提升其整体分类性能,可作为电力变压器故障诊断的重要数据预处理环节。

关键词(KeyWords)： 变压器故障诊断;非均衡数据集;数据增强;条件式Wasserstein生成对抗网络;梯度惩罚;栈式自编码器

Abstract:

Keywords:

基金项目(Foundation): 国家电网有限公司总部科技项目(5204DY170010)~~

作者(Author): 刘云鹏;许自强;和家慧;王权;高树国;赵军;

Email:

DOI: 10.13335/j.1000-3673.pst.2019.2416

参考文献(References)：

• [1]廖瑞金，王有元，刘航，等．输变电设备状态评估方法的研究现状[J]．高电压技术，2018,44(11):3454-2464.Liao Ruijin,Wang Youyuan,Liu Hang,et al.Research status of condition assessment method for power equipment[J].High Voltage Engineering,2018,44(11):3454-2464(in Chinese).
• [2]江秀臣，盛戈皞．电力设备状态大数据分析的研究和应用[J]．高电压技术，2018,44(4):1041-1050.Jiang Xiuchen,Sheng Gehao.Research and application of big data analysis of power equipment condition[J].High Voltage Engineering,2018,44(4):1041-1050(in Chinese).
• [3]林峻，严英杰，盛戈皞，等．考虑时间序列关联的变压器在线监测数据清洗[J]．电网技术，2017,41(11):3733-3740.Lin Jun,Yan Yingjie,Sheng Gehao,et al.Online monitoring data cleaning of transformer considering time series correlation[J].Power System Technology,2017,41(11):3733-3740(in Chinese).
• [4]刘云鹏，许自强，李刚，等．人工智能驱动的数据分析技术在电力变压器状态检修中的应用综述[J]．高电压技术，2019,45(2):337-348.Liu Yunpeng,Xu Ziqiang,Li Gang,et al.Review on applications of artificial intelligence driven data analysis technology in condition based maintenance of power transformers[J]. High Voltage Engineering,2019,45(2):337-348(in Chinese).
• [5]代杰杰，宋辉，杨祎，等．基于油中气体分析的变压器故障诊断Re LU-DBN方法[J]．电网技术，2018,42(2):658-664.Dai Jiejie,Song Hui,Yang Yi,et al.Dissolved gas analysis of insulating oil for power transformer fault diagnosis based on Re LUDBN[J]. Power System Technology, 2018, 42(2):658-664(in Chinese).
• [6]荣智海，齐波，李成榕，等．面向变压器油中溶解气体分析的组合DBN诊断方法[J]．电网技术，2019,43(10):3800-3807.Rong Zhihai,Qi Bo,Li Chengrong,et al.Combined DBN diagnosis method for dissolved gas analysis of power transformer oil[J].Power System Technology,2019,43(10):3800-3807(in Chinese).
• [7] Bacha K,Souahlia S,Gossa M.Power transformer fault diagnosis based on dissolved gas analysis by support vector machine[J].Electric Power Systems Research,2012,83(1):73-79.
• [8] Shah A M,Bhalja B R.Fault discrimination scheme for power transformer using random forest technique[J].IET Generation,Transmission&Distribution,2016,10(6):1431-1439.
• [9]黄建明，李晓明，瞿合祚，等．考虑小波奇异信息与不平衡数据集的输电线路故障识别方法[J]．中国电机工程学报，2017,37(11):3099-3107.Huang Jianming,Li Xiaoming,Qu Hezuo,et al.Method for fault type identification of transmission line considering wavelet singular information and unbalanced dataset[J].Proceedings of the CSEE,2017,37(11):3099-3107(in Chinese).
• [10]刘洋，刘洋，许立雄，等．计及数据类别不平衡的海量用户负荷典型特征高性能提取方法[J]．中国电机工程学报，2019,39(14):4093-4104.Liu Yang,Liu Yang,Xu Lixiong,et al.A high performance extraction method for massive user load typical characteristics considering data class imbalance[J].Proceedings of the CSEE,2019,39(14):4093-4104(in Chinese).
• [11]熊冰妍，王国胤，邓维斌．基于样本权重的不平衡数据欠抽样方法[J]．计算机研究与发展，2016,53(11):2613-2622.Xiong Bingyan,Wang Guoyin,Deng Weibin.Under-sampling method based on sample weight for imbalanced data[J].Journal of Computer Research and Development,2016,53(11):2613-2622(in Chinese).
• [12] Batista G E,Prati R C,Monard M C.A study of the behavior of several methods for balancing machine learning training data[J].ACM SIGKDD Explorations Newsletter,2004,6(1):20-29.
• [13] Chawla N V,Bowyer K W,Hall L O,et al.SMOTE:synthetic minority over-sampling technique[J].Journal of Artificial Intelligence Research,2002(16):321-357.
• [14] Han Hui,Wang Wenyuan,Mao Binghuan.Borderline-SMOTE:a new over-sampling method in imbalanced data sets learning[C]//International Conference on Intelligent Computing,Hefei,China,2005:878-887.
• [15] Douzas G,Bacao F,Last F.Improving imbalanced learning through a heuristic oversampling method based on k-means and SMOTE[J].Information Sciences,2018(465):1-20.
• [16]李艳霞，柴毅，胡友强，等．不平衡数据分类方法综述[J]．控制与决策，2019,34(4):673-688.Li Yanxia,Chai Yi,Hu Youqiang,et al.Review of imbalanced data classification methods[J].Control and Decision,2019,34(4):673-688(in Chinese).
• [17] Goodfellow I,Pouget-Abadie J,Mirza M,et al.Generative adversarial nets[C]//Conference on Neural Information Processing Systems,Montreal,Canada,2014:2672-2680.
• [18] Arjovsky M,Chintala S,Bottou L.Wasserstein generative adversarial networks[C]//International Conference on Machine Learning,Sydney,Australia,2017:214-223.
• [19] Douzas G,Bacao F.Effective data generation for imbalanced learning using conditional generative adversarial networks[J].Expert Systems With Applications,2018,91:464-471.
• [20] Dong J,Yin R,Sun X,et al.Inpainting of remote sensing SST images with deep convolutional generative adversarial network[J].IEEE Geoscience and Remote Sensing Letters,2018,16(2):173-177.
• [21]唐贤伦，杜一铭，刘雨微，等．基于条件深度卷积生成对抗网络的图像识别方法[J]．自动化学报，2018,44(5):855-864.Tang Xianlun,Du Yiming,Liu Yuwei,et al.Image recognition with conditional deep convolutional generative adversarial networks[J].Acta Automatica Sinica,2018,44(5):855-864(in Chinese).
• [22] Sriram A,Jun H,Gaur Y,et al.Robust speech recognition using generative adversarial networks[C]//IEEE International Conference on Acoustics,Speech and Signal Processing,Calgary,Canada,2018:5639-5643.
• [23]王守相，陈海文，潘志新，等．采用改进生成式对抗网络的电力系统量测缺失数据重建方法[J]．中国电机工程学报，2019,39(1):56-64.Wang Shouxiang,Chen Haiwen,Pan Zhixin,et al.A reconstruction method for missing data in power system measurement using an improved generative adversarial network[J]. Proceedings of the CSEE,2019,39(1):56-64(in Chinese).
• [24]刘建伟，谢浩杰，罗雄麟．生成对抗网络在各领域应用研究进展[J/OL]．自动化学报：1-38[2020-01-05].https://doi.org/10.16383/j.aas.c180831.Liu Jianwei,Xie Haojie,Luo Xionglin.Research progress on application of generative adversarial networks in various fields[J/OL].Acta Automatica Sinica:1-38[2020-01-05].https://doi.org/10.16383/j.aas.c180831(in Chinese).
• [25] Gulrajani I,Ahmed F,Arjovsky M,et al.Improved training of wasserstein gans[C]//Conference on Neural Information Processing Systems,Long Beach,USA,2017:5767-5777.
• [26]刘云鹏，许自强，董王英，等．基于经验模态分解和长短期记忆神经网络的变压器油中溶解气体浓度预测方法[J]．中国电机工程学报，2019,39(13):3998-4007.Liu Yunpeng,Xu Ziqiang,Dong Wangying,et al.Concentration prediction of dissolved gases in transformer oil based on empirical mode decomposition and long short-term memory neural networks[J].Proceedings of the CSEE,2019,39(13):3998-4007(in Chinese).
• [27]廖伟涵，郭创新，金宇，等．基于四阶段预处理与GBDT的油浸式变压器故障诊断方法[J]．电网技术，2019,43(6):2195-2203.Liao Weihan,Guo Chuangxin,Jin Yu,et al.Oil-immersed transformer fault diagnosis method based on four-stage preprocessing and GBDT[J].Power System Technology,2019,43(6):2195-2203(in Chinese).
• [28]孙才新，陈伟根，李俭，等．电气设备油中气体在线监测与故障诊断技术[M]．北京：科学出版社，2003:78-82.
• [29] IEC.IEC 60599—2007 Mineral oil-impregnated electrical equipment in service guide to the interpretation of dissolved and free gases analysis[S].Geneva:IEC,2007.
• [30]朱乔木，陈金富，李弘毅，等．基于堆叠自动编码器的电力系统暂态稳定评估[J]．中国电机工程学报，2018,38(10):2937-2946.Zhu Qaiomu,Chen Jinfu,Li Hongyi,et al.Transient stability assessment based on stacked autoencoder[J].Proceedings of the CSEE,2018,38(10):2937-2946(in Chinese).
• [31]石鑫，朱永利，宁晓光，等．基于深度自编码网络的电力变压器故障诊断[J]．电力自动化设备，2016,36(5):122-126.Shi Xin,Zhu Yongli,Ning Xiaoguang,et al.Transformer fault diagnosis based on deep auto-encoder network[J].Electric Power Automation Equipment,2016,36(5):122-126(in Chinese).
• [32]陈欢，彭辉，舒乃秋，等．基于蝙蝠算法优化最小二乘双支持向量机的变压器故障诊断[J]．高电压技术，2018,44(11):3664-3671.Chen Huan,Peng Hui,Shu Naiqiu,et al.Fault diagnosis of transformer based on LS-TSVM optimized by bat algorithm[J].High Voltage Engineering,2018,44(11):3664-3671(in Chinese).
• [33]毕建权，鹿鸣明，郭创新，等．一种基于多分类概率输出的变压器故障诊断方法[J]．电力系统自动化，2015,39(5):88-93+100.Bi Jianquan,Lu Mingming,Guo Chuangxin,et al.A transformer fault diagnosing method based on multi-classified probability output[J].Automation of Electric Power Systems,2015,39(5):88-93+100(in Chinese).
• [34]朱永利，尹金良．组合核相关向量机在电力变压器故障诊断中的应用研究[J]．中国电机工程学报，2013,33(22):68-74.Zhu Yongli,Yin Jinliang.Study on application of multi-kernel learning relevance vector machines in fault diagnosis of power transformers[J].Proceedings of the CSEE,2013,33(22):68-74(in Chinese).
• [35]周志华．机器学习[M]．北京：清华大学出版社，2016:28-37.
• [36] Liu Yufei,Zhou Yuan,Liu Xin,et al.Wasserstein GAN-based small-sample augmentation for new-generation artificial intelligence:A case study of cancer-staging data in biology[J].Engineering,2019,5(1):156-163.
• [37]姚乃明，郭清沛，乔逢春，等．基于生成式对抗网络的鲁棒人脸表情识别[J]．自动化学报，2018,44(5):865-877.Yao Naiming,Guo Qingpei,Qiao Fengchun,et al.Robust facial expression recognition with generative adversarial networks[J].Acta Automatica Sinica,2018,44(5):865-877(in Chinese).
• [38]谭本东，杨军，赖秋频，等．基于改进CGAN的电力系统暂态稳定评估样本增强方法[J]．电力系统自动化，2019,43(1):149-157.Tan Bendong,Yang Jun,Lai Qiupin,et al.Data augment method for power system transient stability assessment based on improved conditional generative adversarial network[J].Automation of Electric Power Systems,2019,43(1):149-157(in Chinese).