基于改进深度降噪自编码网络的电网气象防灾方法
|
摘要
电网运维数据表明电网故障的主要原因已由电气设备制造工艺水平、现场运维水平等因素转向雷电、山火、大风、冰灾等自然气象因素,电网防灾减灾也应重点关注气象致灾。针对气象与电网故障之间的关联特点和规律,提出了一种基于改进深度降噪自编码(SDAE)网络的电网气象防灾方法。以气象历史数据和电网运维检修数据为基础,利用合成少数类样本过采样技术(SMOTE)降低原始数据集的不平衡度,自编码网络通过非监督自学习和有监督微调完成气象信息特征的提取和气象信息与电网故障映射关系的建立,并通过融入稀疏项限制和加噪编码来改善网络的鲁棒性。算例分析表明,所提出的基于SMOTE和SDAE的网络电网气象防灾方法,能够准确、全面地建立气象信息与电网故障之间的关联映射关系,能够对给定的气象条件是否会导致发生电网灾害事故进行准确的预判。
The operation and maintenance data of power grid show that the main causes of the power grid fault have shifted from the level of manufacturing technology of electric equipment and the level of on-site operation and maintenance to natural weather factors such as thunder and lightning,mountain fire,gale and icy disaster.Disaster prevention and mitigation of power grid should also focus on meteorological disaster.Aiming at the characteristics and regularities of association between meteorological and power grid faults,a method of grid weather disaster mitigation based on improved stacked denoising auto-encoder(SDAE)network is proposed.Based on the meteorological historical data and grid operation and maintenance data,the synthetic minority over-sampling technique(SMOTE)is used to reduce the imbalance of the original data set.Auto-encoder network completes the extraction of meteorological information features and the establishment of the relationship meteorological information and grid faults through unsupervised self-learning and supervised fine-tuning,and improves the robustness of the network by incorporating sparse term restrictions and noise-enhanced coding.The case study shows that the proposed SMOTESDAE-based meteorological disaster mitigation method can establish the correlation mapping relationship between meteorological information and power grid fault accurately and completely,and can make accurate prediction for whether the given meteorological conditions will cause grid disaster accidents or not.
The operation and maintenance data of power grid show that the main causes of the power grid fault have shifted from the level of manufacturing technology of electric equipment and the level of on-site operation and maintenance to natural weather factors such as thunder and lightning,mountain fire,gale and icy disaster.Disaster prevention and mitigation of power grid should also focus on meteorological disaster.Aiming at the characteristics and regularities of association between meteorological and power grid faults,a method of grid weather disaster mitigation based on improved stacked denoising auto-encoder(SDAE)network is proposed.Based on the meteorological historical data and grid operation and maintenance data,the synthetic minority over-sampling technique(SMOTE)is used to reduce the imbalance of the original data set.Auto-encoder network completes the extraction of meteorological information features and the establishment of the relationship meteorological information and grid faults through unsupervised self-learning and supervised fine-tuning,and improves the robustness of the network by incorporating sparse term restrictions and noise-enhanced coding.The case study shows that the proposed SMOTESDAE-based meteorological disaster mitigation method can establish the correlation mapping relationship between meteorological information and power grid fault accurately and completely,and can make accurate prediction for whether the given meteorological conditions will cause grid disaster accidents or not.
引文
[1]谢强,李杰.电力系统自然灾害的现状与对策[J].自然灾害学报,2006,15(4):126-131.XIE Qiang,LI Jie.Current situation of natural disaster in electric power system and counter measures[J].Journal of National Disasters,2006,15(4):126-131.
[2]虢韬,刘锐,沈平,等.基于电力大数据的输电线路防灾减灾分析系统设计---以贵州电网为例[J].灾害学,2016,31(1):135-138.GUO Tao,LIU Rui,SHEN Ping,et al.A disaster prevention and reduction analysis system in transmission line based on power big data-a case study on Guizhou power grid[J].Journal of Catastrophology,2016,36(1):135-138.
[3]王德文.基于云计算的电力数据中心基础架构及其关键技术[J].电力系统自动化,2012,36(11):67-71.WANG Dewen.Basic framework and key technology for a new generation of data center in electric power corporation based on cloud computation[J].Automation of Electric Power Systems,2012,36(11):67-71.
[4]贺蓉,曾刚,姚建刚,等.天气敏感型神经网络在地区电网短期负荷预测中的应用[J].电力系统自动化,2001,25(17):32-35.HE Rong,ZENG Gang,YAO Jiangang,et al.Application of weather sensitivity neural network model in short term load forecasting on area[J].Automation of Electric Power Systems,2001,25(17):32-35.
[5]王鹏,邰能灵,王波,等.针对气象因素的短期负荷预测修正方法[J].电力系统自动化,2008,32(13):92-96.WANG Peng,TAI Nengling,WANG Bo,et al.A short-term load forecasting correction method considering climatic factors[J].Automation of Electric Power Systems,2008,32(13):92-96.
[6]谢云云,薛禹胜,文福拴,等.冰灾对输电线故障率影响的时空评估[J].电力系统自动化,2013,37(18):32-41.XIE Yunyun,XUE Yusheng,WEN Fushuan,et al.Space-time evaluation for impact of ice disaster on transmission line fault probability[J].Automation of Electric Power Systems,2013,37(18):32-41.
[7]郑传材,管霖,梁英杰.基于影响因素识别的架空输电线路可靠性管理系统和评估模型[J].电网技术,2009,33(20):158-163.ZHENG Chuancai,GUAN Lin,LIANG Yingjie.Impacting factor recognition based reliability management system for overhead transmission lines and its evaluation model[J].Power System Technology,2009,33(20):158-163.
[8]梁允,李哲,李帅,等.数值天气预报结果在河南电网生产中的应用[J].河南科技,2016(15):46-49.LIANG Yun,LI Zhe,LI Shuai,et al.Application of numerical weather prediction results in grid production of Henan[J].Journal of Henan Science and Technology,2016(15):46-49.
[9]薛禹胜,吴勇军,谢云云,等.停电防御框架向自然灾害预警的拓展[J].电力系统自动化,2013,37(16):18-26.XUE Yusheng,WU Yongjun,XIE Yunyun,et al.Extension of blackout defense scheme to natural disasters early-warning[J].Automation of Electric Power Systems,2013,37(16):18-26.
[10]吴勇军,薛禹胜,谢云云,等.台风及暴雨对电网故障率的时空影响[J].电力系统自动化,2016,40(2):20-29.DOI:10.7500/AEPS20151110014.WU Yongjun,XUE Yusheng,XIE Yunyun,et al.Space-time impact of typhoon and rainstorm on power grid fault probability[J].Automation of Electric Power Systems,2016,40(2):20-29.DOI:10.7500/AEPS20151110014.
[11]吴勇军,薛禹胜,陆佳政,等.山火灾害对电网故障率的时空影响[J].电力系统自动化,2016,40(3):14-20.DOI:10.7500/AEPS20151110015.WU Yongjun,XUE Yusheng,LU Jiazheng,et al.Space-time impact of forest fire on power grid fault probability[J].Automation of Electric Power Systems,2016,40(3):14-20.DOI:10.7500/AEPS20151110015.
[12]孙世军,张治取,韩洪.疑似火点监测定位及电网运行预警方法[J].中国电力,2017,50(4):181-184.SUN Shijun,ZHANG Zhiqu,HAN Hong.Study on the method of power network operation early warning using remote sensor monitoring and locating of satellites based on power grid GIS[J].Electric Power,2017,50(4):181-184.
[13]PAN W,ZHONG S,HUANG S,et al.Online power grid emergency material demand forecasting model in typhoon disaster based on relevance vector machine[C]//9th International Symposium on Computational Intelligence and Design(ISCID),December 10-11,2016,Hangzhou,China.
[14]LIU Y,SINGH C.A methodology for evaluation of hurricane impact on composite power system reliability[J].IEEETransactions on Power Systems,2011,26(1):145-152.
[15]黄宵宁,许家浩,杨成顺,等.基于数据驱动算法和LS-SVM的输电线路覆冰预测[J].电力系统自动化,2014,38(15):81-86.DOI:10.7500/AEPS20131022011.HUANG Xiaoning,XU Jiahao,YANG Chengshun,et al.Transmission line icing prediction based on data driven algorithm and LS-SVM[J].Automation of Electric Power Systems,2014,38(15):81-86.DOI:10.7500/AEPS20131022011.
[16]孙文珺,邵思羽,严如强.基于稀疏自动编码深度神经网络的感应电动机故障诊断[J].机械工程学报,2016,52(9):65-71.SUN Wenjun,SHAO Siyu,YAN Ruqiang.Induction motor fault diagnosis based on deep neural network of sparse autoencoder[J].Journal of Machanical Engineering,2016,52(9):65-71.
[17]朱煜奇,黄双喜,杨天祺,等.基于栈式降噪自编码的故障诊断[J].制造业自动化,2017,39(3):152-156.ZHU Yuqi,HUANG Shuangxi,YANG Tianqi,et al.Fault diagnosis based on stacked denoising autoencoder[J].Manufacturing Automation,2017,39(3):152-156.
[18]HINTON G,SALAKHUTDINOV R.Reducing the dimensionality of data with neural networks[J].Science,2006,313:504.
[19]LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521:436-444.
[20]鞠建波,胡胜林,祝超,等.基于深度学习的装备故障诊断方法[J].电光与控制,2018(2):1-5.JU Jianbo,HU Shenglin,ZHU Chao,et al.A deep learningbased method for equipment fault diagnosis[J].Electronics and Control,2018(2):1-5.
[21]任浩,屈剑锋,柴毅,等.深度学习在故障诊断领域中的研究现状与挑战[J].控制与决策,2017,32(8):1345-1358.REN Hao,QU Jianfeng,CHAI Yi,et al.Deep learning for fault diagnosis:the state of the art and challenge[J].Control and Decision,2017,32(8):1345-1358.
[22]赵洪山,刘辉海.基于性能改善深度置信网络的风电机组主轴承状态分析[J].电力自动化设备,2018,38(2):44-49.ZHAO Hongshan,LIU Huihai.Condition analysis of wind turbine main bearing based on deep belief network with improved performance[J].Electric Power Automation Equipment,2018,38(2):44-49.
[23]魏东,龚庆武,来文青,等.基于卷积神经网络的输电线路区内外故障判断及故障选相方法研究[J].中国电机工程学报,2016,36(增刊1):21-28.WEI Dong,GONG Qingwu,LAI Wenqing,et al.Research on internal and external fault diagnosis and fault-selection of transmission line based on convolutional neural network[J].Proceedings of the CSEE,2016,36(Supplement 1):21-28.
[24]朱乔木,党杰,陈金富,等.基于深度置信网络的电力系统暂态稳定评估方法[J].中国电机工程学报,2018,38(3):935-743.ZHU Qiaomu,DANG Jie,CHEN Jinfu,et al.A method for power system transient stability assessment based on deep belief networks[J].Proceedings of the CSEE,2018,38(3):935-743.
[25]刘辉海,赵星宇,赵洪山,等.基于深度自编码网络模型的风电机组齿轮箱故障检测[J].电工技术学报,2017,32(17):156-163.LIU Huihai,ZHAO Xingyu,ZHAO Hongshan,et al.Fault detection of wind turbine gearbox based on deep autoencoder network[J].Transactions of China Electrotechnical Society,2017,32(17):156-163.
[26]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 Qiaomu,CHEN Jinfu,LI Hongyi,et al.Transient stability assessment based on stacked autoencoder[J].Proceedings of the CSEE,2018,38(10):2937-2946.
[27]代杰杰,宋辉,杨祎,等.基于栈式降噪自编码器的输变电设备状态数据清洗方法[J].电力系统自动化,2017,41(12):224-230.DOI:10.7500/AEPS20161201003.DAI Jiejie,SONG Hui,YANG Yi,et al.Cleaning method for status data of power transmission and transformation equipment based on stacked denoising autoencoders[J].Automation of Electric Power Systems,2017,41(12):224-230.DOI:10.7500/AEPS20161201003.
[28]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.
[29]胡伟,郑乐,闵勇,等.基于深度学习的电力系统故障后暂态稳定评估研究[J].电网技术,2017,41(10):3140-3146.HU Wei,ZHENG Le,MIN Yong,et al.Research on power system transient stability assessment based on deep learning of big data technique[J].Power System Technology,2017,41(10):3140-3146.
[2]虢韬,刘锐,沈平,等.基于电力大数据的输电线路防灾减灾分析系统设计---以贵州电网为例[J].灾害学,2016,31(1):135-138.GUO Tao,LIU Rui,SHEN Ping,et al.A disaster prevention and reduction analysis system in transmission line based on power big data-a case study on Guizhou power grid[J].Journal of Catastrophology,2016,36(1):135-138.
[3]王德文.基于云计算的电力数据中心基础架构及其关键技术[J].电力系统自动化,2012,36(11):67-71.WANG Dewen.Basic framework and key technology for a new generation of data center in electric power corporation based on cloud computation[J].Automation of Electric Power Systems,2012,36(11):67-71.
[4]贺蓉,曾刚,姚建刚,等.天气敏感型神经网络在地区电网短期负荷预测中的应用[J].电力系统自动化,2001,25(17):32-35.HE Rong,ZENG Gang,YAO Jiangang,et al.Application of weather sensitivity neural network model in short term load forecasting on area[J].Automation of Electric Power Systems,2001,25(17):32-35.
[5]王鹏,邰能灵,王波,等.针对气象因素的短期负荷预测修正方法[J].电力系统自动化,2008,32(13):92-96.WANG Peng,TAI Nengling,WANG Bo,et al.A short-term load forecasting correction method considering climatic factors[J].Automation of Electric Power Systems,2008,32(13):92-96.
[6]谢云云,薛禹胜,文福拴,等.冰灾对输电线故障率影响的时空评估[J].电力系统自动化,2013,37(18):32-41.XIE Yunyun,XUE Yusheng,WEN Fushuan,et al.Space-time evaluation for impact of ice disaster on transmission line fault probability[J].Automation of Electric Power Systems,2013,37(18):32-41.
[7]郑传材,管霖,梁英杰.基于影响因素识别的架空输电线路可靠性管理系统和评估模型[J].电网技术,2009,33(20):158-163.ZHENG Chuancai,GUAN Lin,LIANG Yingjie.Impacting factor recognition based reliability management system for overhead transmission lines and its evaluation model[J].Power System Technology,2009,33(20):158-163.
[8]梁允,李哲,李帅,等.数值天气预报结果在河南电网生产中的应用[J].河南科技,2016(15):46-49.LIANG Yun,LI Zhe,LI Shuai,et al.Application of numerical weather prediction results in grid production of Henan[J].Journal of Henan Science and Technology,2016(15):46-49.
[9]薛禹胜,吴勇军,谢云云,等.停电防御框架向自然灾害预警的拓展[J].电力系统自动化,2013,37(16):18-26.XUE Yusheng,WU Yongjun,XIE Yunyun,et al.Extension of blackout defense scheme to natural disasters early-warning[J].Automation of Electric Power Systems,2013,37(16):18-26.
[10]吴勇军,薛禹胜,谢云云,等.台风及暴雨对电网故障率的时空影响[J].电力系统自动化,2016,40(2):20-29.DOI:10.7500/AEPS20151110014.WU Yongjun,XUE Yusheng,XIE Yunyun,et al.Space-time impact of typhoon and rainstorm on power grid fault probability[J].Automation of Electric Power Systems,2016,40(2):20-29.DOI:10.7500/AEPS20151110014.
[11]吴勇军,薛禹胜,陆佳政,等.山火灾害对电网故障率的时空影响[J].电力系统自动化,2016,40(3):14-20.DOI:10.7500/AEPS20151110015.WU Yongjun,XUE Yusheng,LU Jiazheng,et al.Space-time impact of forest fire on power grid fault probability[J].Automation of Electric Power Systems,2016,40(3):14-20.DOI:10.7500/AEPS20151110015.
[12]孙世军,张治取,韩洪.疑似火点监测定位及电网运行预警方法[J].中国电力,2017,50(4):181-184.SUN Shijun,ZHANG Zhiqu,HAN Hong.Study on the method of power network operation early warning using remote sensor monitoring and locating of satellites based on power grid GIS[J].Electric Power,2017,50(4):181-184.
[13]PAN W,ZHONG S,HUANG S,et al.Online power grid emergency material demand forecasting model in typhoon disaster based on relevance vector machine[C]//9th International Symposium on Computational Intelligence and Design(ISCID),December 10-11,2016,Hangzhou,China.
[14]LIU Y,SINGH C.A methodology for evaluation of hurricane impact on composite power system reliability[J].IEEETransactions on Power Systems,2011,26(1):145-152.
[15]黄宵宁,许家浩,杨成顺,等.基于数据驱动算法和LS-SVM的输电线路覆冰预测[J].电力系统自动化,2014,38(15):81-86.DOI:10.7500/AEPS20131022011.HUANG Xiaoning,XU Jiahao,YANG Chengshun,et al.Transmission line icing prediction based on data driven algorithm and LS-SVM[J].Automation of Electric Power Systems,2014,38(15):81-86.DOI:10.7500/AEPS20131022011.
[16]孙文珺,邵思羽,严如强.基于稀疏自动编码深度神经网络的感应电动机故障诊断[J].机械工程学报,2016,52(9):65-71.SUN Wenjun,SHAO Siyu,YAN Ruqiang.Induction motor fault diagnosis based on deep neural network of sparse autoencoder[J].Journal of Machanical Engineering,2016,52(9):65-71.
[17]朱煜奇,黄双喜,杨天祺,等.基于栈式降噪自编码的故障诊断[J].制造业自动化,2017,39(3):152-156.ZHU Yuqi,HUANG Shuangxi,YANG Tianqi,et al.Fault diagnosis based on stacked denoising autoencoder[J].Manufacturing Automation,2017,39(3):152-156.
[18]HINTON G,SALAKHUTDINOV R.Reducing the dimensionality of data with neural networks[J].Science,2006,313:504.
[19]LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521:436-444.
[20]鞠建波,胡胜林,祝超,等.基于深度学习的装备故障诊断方法[J].电光与控制,2018(2):1-5.JU Jianbo,HU Shenglin,ZHU Chao,et al.A deep learningbased method for equipment fault diagnosis[J].Electronics and Control,2018(2):1-5.
[21]任浩,屈剑锋,柴毅,等.深度学习在故障诊断领域中的研究现状与挑战[J].控制与决策,2017,32(8):1345-1358.REN Hao,QU Jianfeng,CHAI Yi,et al.Deep learning for fault diagnosis:the state of the art and challenge[J].Control and Decision,2017,32(8):1345-1358.
[22]赵洪山,刘辉海.基于性能改善深度置信网络的风电机组主轴承状态分析[J].电力自动化设备,2018,38(2):44-49.ZHAO Hongshan,LIU Huihai.Condition analysis of wind turbine main bearing based on deep belief network with improved performance[J].Electric Power Automation Equipment,2018,38(2):44-49.
[23]魏东,龚庆武,来文青,等.基于卷积神经网络的输电线路区内外故障判断及故障选相方法研究[J].中国电机工程学报,2016,36(增刊1):21-28.WEI Dong,GONG Qingwu,LAI Wenqing,et al.Research on internal and external fault diagnosis and fault-selection of transmission line based on convolutional neural network[J].Proceedings of the CSEE,2016,36(Supplement 1):21-28.
[24]朱乔木,党杰,陈金富,等.基于深度置信网络的电力系统暂态稳定评估方法[J].中国电机工程学报,2018,38(3):935-743.ZHU Qiaomu,DANG Jie,CHEN Jinfu,et al.A method for power system transient stability assessment based on deep belief networks[J].Proceedings of the CSEE,2018,38(3):935-743.
[25]刘辉海,赵星宇,赵洪山,等.基于深度自编码网络模型的风电机组齿轮箱故障检测[J].电工技术学报,2017,32(17):156-163.LIU Huihai,ZHAO Xingyu,ZHAO Hongshan,et al.Fault detection of wind turbine gearbox based on deep autoencoder network[J].Transactions of China Electrotechnical Society,2017,32(17):156-163.
[26]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 Qiaomu,CHEN Jinfu,LI Hongyi,et al.Transient stability assessment based on stacked autoencoder[J].Proceedings of the CSEE,2018,38(10):2937-2946.
[27]代杰杰,宋辉,杨祎,等.基于栈式降噪自编码器的输变电设备状态数据清洗方法[J].电力系统自动化,2017,41(12):224-230.DOI:10.7500/AEPS20161201003.DAI Jiejie,SONG Hui,YANG Yi,et al.Cleaning method for status data of power transmission and transformation equipment based on stacked denoising autoencoders[J].Automation of Electric Power Systems,2017,41(12):224-230.DOI:10.7500/AEPS20161201003.
[28]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.
[29]胡伟,郑乐,闵勇,等.基于深度学习的电力系统故障后暂态稳定评估研究[J].电网技术,2017,41(10):3140-3146.HU Wei,ZHENG Le,MIN Yong,et al.Research on power system transient stability assessment based on deep learning of big data technique[J].Power System Technology,2017,41(10):3140-3146.