曹瑞峰,刘子华,袁婷,罗扬帆,茹传红,秦建,邢海军
CAO Ruifeng,LIU Zihua,YUAN Ting,LUO Yangfan,RU Chuanhong,QIN Jian,XING Haijun

• 1:国网浙江省电力有限公司
• 2:国网浙江省电力有限公司台州供电公司
• 3:上海电力大学电气工程学院

摘要(Abstract)：

新能源电站运行数据量大、运行工况多变，发电机组的故障诊断难度较大。为此，提出了一种基于改进SVM算法的新能源电站故障诊断方法。首先，对SVM（支持向量机）的概念和原理进行了分析，并采用多元SVM分类器对SVM进行优化；然后，研究了光伏电站和风电站的故障信号提取和故障特征分析方法，并在此基础上提出了故障诊断模型；最后，从实际新能源电站获取样本数据，构建了基于决策级融合的改进SVM故障诊断模型，并将故障特征向量输入模型进行训练。结果表明，针对光伏电站的故障诊断准确率达到了97.5%，风电站的故障诊断准确率达到了98.09%，验证了该方法的准确性。
New energy power plants generate vast amounts of operational data and experience highly variable operating conditions, posing a significant challenge when it comes to diagnosing faults in generator sets. For this reason, a fault diagnosis model based on an improved SVM(support vector machine) algorithm is introduced. Firstly, the concept and principle of SVM for new energy power plants are analyzed. A multivariate SVM classifier is used to optimize the SVM. Secondly, the fault signal extraction method and fault characterization method of photovoltaic power stations and wind farms are studied. Moreover, a fault diagnosis model is proposed. Finally, sample data are obtained from new energy power plants, and an improved SVM fault diagnosis model based on decision level fusion is built. Additionally, the model is trained using fault feature vectors. The results show that the fault diagnosis accuracy for photovoltaic power plants reaches 97.5%, while the fault diagnosis accuracy for wind farms reaches 98.09%, which verify the accuracy of the method.

关键词(KeyWords)： SVM;故障诊断;特征提取;光伏电站;风电机组
SVM;fault diagnosis;feature extraction;photovoltaic power station;wind turbine generator system

Abstract:

Keywords:

基金项目(Foundation): 国网浙江省电力有限公司科技项目（5211TZ220002）

作者(Author): 曹瑞峰,刘子华,袁婷,罗扬帆,茹传红,秦建,邢海军
CAO Ruifeng,LIU Zihua,YUAN Ting,LUO Yangfan,RU Chuanhong,QIN Jian,XING Haijun

DOI: 10.19585/j.zjdl.202311002

参考文献(References)：

• [1]李晖，刘栋，姚丹阳.面向碳达峰碳中和目标的我国电力系统发展研判[J].中国电机工程学报，2021,41(18):6245-6259.LI Hui,LIU Dong,YAO Danyang. Analysis and reflection on the development of power system towards the goal of carbon emission peak and carbon neutrality[J].Proceedings of the CSEE,2021,41(18):6245-6259.
• [2]程超，周渝慧，岳开伟，等.城市绿色电力战略环境评价指标体系[J].中国电力，2012,45(3):76-80.CHENG Chao,ZHOU Yuhui,YUE Kaiwei,et al.Indicators system of strategic environmental assessment for urban green electricity power[J]. Electric Power,2012,45(3):76-80.
• [3]李延和，杨立滨，郝丽丽，等.基于改进样板机法的风光互补新能源电站容量配比优化[J].电力工程技术，2022,41(2):224-233.LI Yanhe,YANG Libin,HAO Lili,et al. Capacity ratio optimization of wind-solar hybrid new energy power station based on improved model-generator method[J].Electric Power Engineering Technology,2022,41(2):224-233.
• [4]傅旭，杨欣，汪莹，等.光热电站容量效益评估及影响因素研究[J].电力工程技术，2021,40(3):186-192.FU Xu,YANG Xin,WANG Ying,et al.The capacity benefit evaluation of CSP power station and its influencing factors[J].Electric Power Engineering Technology,2021,40(3):186-192.
• [5] ZHAO Y,YANG L,LEHMAN B,et al. Decision treebased fault detection and classification in solar photovoltaic arrays[C]//2012 Twenty-Seventh Annual IEEE Applied Power Electronics Conference and Exposition(APEC).February 5-9,2012,Orlando,FL,USA.IEEE,2012:93-99.
• [6]张李炜，李孝忠.基于Apriori算法和卷积神经网络的风电机组故障诊断模型[J].天津科技大学学报，2022,37(5):50-55.ZHANG Liwei,LI Xiaozhong. Fault diagnosis model of wind turbine based on apriori and convolutional neural network[J].Journal of Tianjin University of Science&Technology,2022,37(5):50-55.
• [7]黄宇斐，石新发，贺石中，等.一种基于主成分分析与支持向量机的风电齿轮箱故障诊断方法[J].热能动力工程，2022,37(10):175-181.HUANG Yufei,SHI Xinfa,HE Shizhong,et al.A fault diagnosis method of wind turbine gearbox based on PCA and SVM[J].Journal of Engineering for Thermal Energy and Power,2022,37(10):175-181.
• [8]王方政，刘喜泉，陈浈斐，等.基于串联电阻估计的光伏阵列热斑故障诊断方法[J].智慧电力，2022,50(10):61-69.WANG Fangzheng,LIU Xiquan,CHEN Zhenfei,et al.Hot spot failure diagnosis method for photovoltaic array based on series resistance estimation[J]. Smart Power,2022,50(10):61-69.
• [9]刘开石，李田泽，刘东，等.基于ABC-SVM算法的光伏阵列故障诊断[J].电源技术，2021,45(9):1171-1174.LIU Kaishi,LI Tianze,LIU Dong,et al.Fault diagnosis of PV array based on ABC-SVM algorithm[J].Chinese Journal of Power Sources,2021,45(9):1171-1174.
• [10]武天府，刘征，王志强，等.基于Focal损失SSDAE的变压器故障诊断方法[J].电力工程技术，2021,40(6):18-24.WU Tianfu,LIU Zheng,WANG Zhiqiang,et al. Transformer fault diagnosis method based on Focal loss SSDAE[J].Electric Power Engineering Technology,2021,40(6):18-24.
• [11]宰红斌，吴浩林，王昊，等.基于改进机器学习的输电线路弧垂温度估计方法[J].电力工程技术，2022,41(2):209-214.ZAI Hongbin,WU Haolin,WANG Hao,et al. Sag and temperature estimation method based on improved machine learning for transmission line[J].Electric Power Engineering Technology,2022,41(2):209-214.
• [12]邓奇.基于改进LMD和粒子群优化最小二乘支持向量机的风电机组齿轮箱故障诊断[D].西安：西安理工大学，2021.DENG Qi.Fault diagnosis of wind turbine gearbox based on improved LMD and particle swarm optimization least square support vector machine[D].Xi'an:Xi'an University of Technology,2021.
• [13]邱海枫，苏宁，田松林.改进支持向量机在电力变压器故障诊断中的应用研究[J].电测与仪表，2022,59(11):48-53.QIU Haifeng,SU Ning,TIAN Songlin. Research on the application of improved support vector machine in power transformer fault diagnosis[J].Electrical Measurement&Instrumentation, 2022,59(11):48-53.
• [14]王奉涛，马孝江，朱泓，等.基于Dempster-Shafer证据理论的信息融合在设备故障诊断中应用[J].大连理工大学学报，2003,43(4):470-474.WANG Fengtao,MA Xiaojiang,ZHU Hong,et al. Research on fault diagnosis method based on DempsterShafer evidential theory[J].Journal of Dalian University of Technology,2003,43(4):470-474.
• [15]陈国成，张建，菅光雷.基于改进叠加自动编码器轴承智能故障诊断方法[J].噪声与振动控制，2022,42(1):156-161.CHEN Guocheng,ZHANG Jian,JIAN Guanglei. Intelligent fault diagnosis of bearings based on improved stacked autoencoders[J]. Noise and Vibration Control,2022,42(1):156-161.
• [16]叶进，卢泉，王钰淞，等.基于级联随机森林的光伏故障诊断模型研究[J].太阳能学报，2021,42(3):358-362.YE Jin,LU Quan,WANG Yusong,et al.Research on pv fault diagnosis model based on cascaded random forest[J].Acta Energiae Solaris Sinica,2021,42(3):358-362.
• [17]姚远.基于特征提取的光伏故障诊断研究[D].北京：华北电力大学，2017.YAO Yuan. Research on photovoltaic fault diagnosis based on feature extraction[D].Beijing:North China Electric Power University,2017.
• [18]涂彦昭，高伟，杨耿杰.一种基于卷积神经网络和长短期记忆网络的光伏系统故障辨识方法[J].电气技术，2022,23(2):48-54.TU Yanzhao,GAO Wei,YANG Gengjie.A photovoltaic system fault identification method based on convolutional neural network and long short-term memory network[J].Electrical Engineering,2022,23(2):48-54.
• [19] TANG Z H,WANG M J,OUYANG T H,et al.A wind turbine bearing fault diagnosis method based on fused depth features in time-frequency domain[J]. Energy Reports,2022,8:12727-12739.
• [20]金晓航，孙毅，单继宏，等.风力发电机组故障诊断与预测技术研究综述[J].仪器仪表学报，2017,38(5):1041-1053.JIN Xiaohang,SUN Yi,SHAN Jihong,et al.Fault diagnosis and prognosis for wind turbines:an overview[J].Chinese Journal of Scientific Instrument,2017,38(5):1041-1053.