摘要考虑到传统物理分析方法无法解决导线舞动的预测问题，综合运用机器学习算法，对已有的舞动历史数据进行筛选和预处理，并挖掘有效信息，利用one class SVM算法解决舞动数据中负样本缺失问题，采用集成学习算法中Bagging算法建立分类器学习方法，实现了数据的随机抽样，分成不同组数据集进行相互独立的训练，避免对舞动数据过拟合，提升机器学习算法的抗噪声能力以及泛化能力，采用k折交叉验证算法进行模型的验证，并利用F1-score描述导线舞动预警模型的性能，验证了该方法在舞动预测方面的有效性。
Abstract：Considering that the traditional physical analysis method cannot solve the prediction of conductor galloping, a machine learning algorithm was synthetically used to screen and pre-process the existing dance history data.Mining effective information from the selected and preprocessed data, the one class SVM algorithm was used to carry out an unsupervised learning of the galloping history data.In the training of the galloping prediction model, the Bagging algorithm was used in the ensemble learning algorithm to train the classifier.The monitoring data was randomly sampled into different sets of data sets for independent training, which avoids over-fitting and improves the anti-noise ability and generalization ability of the machine learning algorithm.Using the k-fold cross validation algorithm to verify the accuracy of the prediction model and using the F1-score to describe the performance of the traverse galloping early warning model, the effectiveness of the machine learning method in the aspect of galloping prediction was confirmed.
程永锋，汉京善，刘彬，李鹏，姬昆鹏. 基于Bagging算法构造强分类器的one class SVM 导线舞动预测应用[J]. 振动与冲击, 2020, 39(9): 152-158.
CHENG Yongfeng, HAN Jingshan, LIU Bin,LI Peng, JI Kunpeng. Prediction of transmission line galloping by one class SVM based on the Bagging algorithm for constructing a strong classifier. JOURNAL OF VIBRATION AND SHOCK, 2020, 39(9): 152-158.
[1] 郭应龙， 恽俐丽， 鲍务均，等. 输电导线舞动研究[J]. 武汉大学学报(工学版)，1995(5):506-509.
Guo Yinglong, Yun Li, Bao you Jun, et al. Research on galloping of transmission conductors [J]. Journal of Wuhan University (Engineering Edition), 1995 (5): 506-509.
[2] 梁志峰. 2011-2013年国家电网公司输电线路故障跳闸统计分析[J]. 华东电力，2014，42(11):2265-2270.
Liang Zhi Feng. Statistical analysis of transmission failures of national Power Grid Corp in 2011-2013 years [J]. East China electric power, 2014, 42 (11): 2265-2270.
[3] Den Hartog J P. Transmission line vibration due to sleet[J]. Electrical Engineering，1932， 51(6):413-413.
[4] Den Hartog J P. Mechanical vibrations[M]. McGraw-Hill, 1956.
[5] Nigol O, Buchan P G. Conductor Galloping Part I - Den Hartog Mechanism[J]. IEEE Transactions on Power Apparatus & Systems, 1981, PAS-100(2):699-707.
[6] Nigol O, Buchan P G. Conductor Galloping-Part II Torsional Mechanism[J]. IEEE Transactions on Power Apparatus & Systems, 1981, PAS-100(2):708-720.
[7] Yu P, Shah A H, Popplewell N. Inertially Coupled Galloping of Iced Conductors[J]. Journal of Applied Mechanics-Transactions of the Asme, 1992, 59(1): 140-145.
[8] Yu P, Popplewell N, Shah A H. Instability trends of inertially coupled galloping, part II: Periodic Vibrations[J]. Journal of Sound and vibration, 1995, 183(4):679-691.
[9] 蔡廷湘. 输电线舞动新机理研究[J]. 中国电力, 1998(10).
Cai Tingxiang. Research on New Mechanism of Transmission Line Dancing[J]. China Electric Power, 1998(10).
[10] 马文勇. 覆冰导线驰振试验及理论研究[D]. 同济大学, 2009.
Ma Wenyong. Experimental and theoretical study onthe vibration of ice-covered conductors [D]. Tongji University, 2009.
[11] 蒋兴良, 周仿荣, 王少华,等. 输电导线覆冰舞动机理及防治措施[J]. 电力建设, 2008, 29(9):14-18.
Jiang Xingliang, Zhou Fangrong, Wang Shaohua, et al. Mechanism and prevention measures of ice spreading on transmission lines[J]. Electric Power Construction, 2008, 29(9): 14-18.
[12] 张明升. 架空线路单导线舞动与分裂导线舞动的异同[J]. 河北电力技术, 1990,(1):29-33.
Zhang Mingsheng. Similarities and differences between single-wire galloping and split-wire dancing in overhead lines[J]. Hebei Electric Power Technology, 1990, (1): 29-33.
[13] 石吉汉, 吴继云. 导线舞动的防治[J]. 电力建设, 2005, 26(12):39-42.
Shi Jihan, Wu Jiyun. Prevention and Control of Wire Galloping[J]. Electric Power Construction, 2005, 26(12): 39-42.
[14] 朱宽军, 尤传永, 赵渊如. 输电线路舞动的研究与治理[J]. 电力建设, 2004, 25(12):18-21.
Zhu Kuanjun, You Chuanyong, Zhao Yuanru. Research and Governance of Transmission Line Galloping[J]. Electric Power Construction, 2004, 25(12): 18-21.
[15] 黄经亚. 架空送电线路导线舞动的分析研究[J]. 中国电力, 1995, 28(2):21-26．
Huang Jingya. Analysis and Research on Wire Galloping of Overhead Transmission Lines[J]. China Electric Power, 1995, 28(2): 21-26.
[16] 徐中年. 大气湍流对输电线舞动的影响[J]. 中国电力, 1995(11).
Xu Zhongnian. Influence of atmospheric turbulence on power line galloping[J]. China Electric Power, 1995(11).
[17] RichardsonAS. Predicting Galloping Amplitudes[J]．Journal of Engineering Mechanics，1988. 114(4): 716-723．
[18] Robert C. Machine Learning, a Probabilistic Perspective[J]. Chance, 2014, 27 (2): 62-63.
[19] 赵作利. 输电线路导线舞动及其防治[J]. 高电压技术， 2004， 30(2):57-58.
Zhao J. Li. Conductor galloping of transmission lines and its prevention and control of [J]. high voltage technology, 2004, 30 (2): 57-58
[20] 于俊清， 郭应龙， 肖晓晖. 输电导线舞动的计算机仿真[J]. 武汉大学学报(工学版)， 2002， 35(1):39-43.
Yu Junqing, Guo Yinglong, Xiao Xiaohui. Computer Simulation of Transmission Wire Galloping[J]. Journal of Wuhan University (Engineering Science), 2002, 35(1): 39-43.
[21] 王永灿， 冯远静， 俞立. 基于无线视频传感网的高压塔架监控系统研究[J]. 传感技术学报， 2008， 21(12):2039-2043.
Wang Yongcan, Feng Yuanjing, Yu Li. Research on High Voltage Tower Monitoring System Based on Wireless Video Sensor Network[J]. Journal of Transduction Technology, 2008, 21(12): 2039-2043.
[22] 张学工. 关于统计学习理论与支持向量机[J]. 自动化学报, 2000, 26(1):32-42.
Zhang Xuegong. Statistical learning theory and support vector machine [J]. automation journal, 2000, 26 (1): 32-42.
[23] 黄友平. 贝叶斯网络研究[D]. 中国科学院计算技术研究所, 2005.
Huang Youping. Bayesian network research [D]. Institute of computing technology, Chinese Academy of Sciences, 2005.
[24] 毛毅, 陈稳霖, 郭宝龙,等. 基于密度估计的逻辑回归模型[J]. 自动化学报, 2014, 40(1):62-72.
Mao Yi, Chen Wenlin, Guo Baolong, et al. Logistic regression model based on density estimation [J]. automation journal, 2014, 40 (1): 62-72.
[25] 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):2806-2810.
Sun Zhijun, Xue Lei, Xu Yangming, et al. Summary of deep learning research [J]. computer application research, 2012, 29 (8): 2806-2810.
[26] 刘小虎, 李生. 决策树的优化算法[J]. 软件学报, 1998, 9(10):797-800.
Liu Xiaohu, Li Sheng. Optimization Algorithm for Decision Tree[J]. Journal of Software, 1998, 9(10): 797-800.
[27] 崔伟东, 周志华, 李星. 支持向量机研究[J]. 计算机工程与应用, 2001, 27(1):58-61.
Cui Weidong, Zhou Chinua, Li Xing. Support vector machine research [J]. computer engineering and application, 2001, 27 (1): 58-61.
[28] 克里斯蒂亚尼尼. 支持向量机导论[M]. 电子工业出版社, 2004.
Kristian Nini. Introduction to Support Vector Machines [M]. Publishing House of Electronics Industry, 2004.
[29] Manevitz L M, Yousef M. One-class svms for document classification[J]. Journal of Machine Learning Research, 2002, 2(1):139-154.
[30] Vert R, Vert J P. Consistency and Convergence Rates of One-Class SVMs and Related Algorithms[J]. Journal of Machine Learning Research, 2006, 7(7):817-854.
[31] 李凯, 崔丽娟. 集成学习算法的差异性及性能比较[J]. 计算机工程, 2008, 34(6):35-37.
Li Kai, Cui Lijuan. Differences and performance comparison of ensemble learning algorithms [J]. Computer Engineering, 2008, 34 (6): 35-37.
[32] 于玲, 吴铁军. 集成学习:Boosting算法综述[J]. 模式识别与人工智能, 2004, 17(1):52-59.
Yu Ling, Wu Tiejun. Ensemble learning: Boosting algorithm overview [J]. pattern recognition and artificial intelligence, 2004, 17 (1): 52-59.
[33] 唐伟, 周志华. 基于Bagging的选择性聚类集成[J]. 软件学报, 2005, 16(4):496-502.
Tang Wei, Zhou Zhihua. Journal of selective cluster integration [J]. software based on Bagging, 2005, 16 (4): 496-502.
[34] 胡局新, 张功杰. 基于K折交叉验证的选择性集成分类算法[J]. 科技通报, 2013(12):115-117.
Hu JuXin, Zhang Gongjie. Selective ensemble classification algorithm based on K fold cross validation [J]. science and Technology Bulletin, 2013 (12): 115-117.
[35] Lipton Z C, Elkan C, Narayanaswamy B. Thresholding Classifiers to Maximize F1 Score[J]. Eprint Arxiv, 2014.
