王劭鹤,金涌涛,赵琳,杨勇

• 1:浙江省电力公司电力科学研究院

摘要(Abstract)：

针对气体绝缘金属封闭开关设备（Gas Insulated Switchgear,GIS）早期机械缺陷难以辨识的问题，提出一种基于复合特征优选与改进随机森林的GIS机械故障诊断方法。首先提取GIS振动信号在频谱域和时频图像域的特征参量，进而构造GIS不同机械状态下的复合特征集，其次利用蚁狮算法优化的随机森林计算17维特征值矩阵的重要度并进行特征优选，最后借助于随机森林算法实现GIS不同机械状态的辨识。搭建了包含三种GIS设备典型机械缺陷的实验模拟测试系统并进行了对比实验，结果表明：所提方法提取得到的优选复合特征能够有效表征GIS不同的机械状态，辨识准确率可达98%，相较于常规单一的特征提取方法辨识精度有明显提升。

关键词(KeyWords)： 气体绝缘金属封闭开关;机械缺陷;蚁狮算法;随机森林

Abstract:

Keywords:

基金项目(Foundation): 国网浙江省电力有限公司科技项目（5211DS20008K）

作者(Author): 王劭鹤,金涌涛,赵琳,杨勇

DOI: 10.19356/j.cnki.1001-3997.20251222.035

参考文献(References)：

• [1]谭盛武，宋广民，解国林，等.分段求解的弹簧操动机构断路器合闸优化设计[J].机械设计与制造，2022,374(4):101-104.(Tan Shengwu,Song Guangmin,Xie Guolin,et al.Optimum design of circuit breaker closing of spring operatingmechanism based on piecewise solution[J].Machinery Design&Manufacture,2022,374(4):101-104.)
• [2]孙玉伟，罗林根，陈敬德，等.含噪背景下基于盲源分离与NSVDD的断路器机械故障诊断方法[J].高电压技术，2022,48(3):1104-1113.(Sun Yuwei,Luo Lingen,Chen Jingde,et al. Mechanical fault diagnosis method of circuit breaker based on blind source separation and NSVDD under noisy background[J]. High Voltage Engineering,2022,48(3):1104-1113.)
• [3]Liu Y,Jia Y,Yang J,et al. Research of mechanical state diagnosis techniques in GIS bus connector based on mechanical vibration[C]. 201812th International Conference on the Properties and Applications of Dielectric Materials(ICPADM). IEEE,2018:682-685.
• [4]Stankovic,Ljubisa.A method for time-frequency analysis[J].IEEE Transactions on Signal Processing,1994,42(1):225-229.
• [5]姚杨，林金涛，刘洪正，等.基于复合特征的断路器机械故障诊断方法研究[J].中国电机工程学报，2019,39(21):6439-6452.(Yao Yang,Lin Jintao,Liu Hongzheng,et al. Research on mechanical fault diagnosis of circuit breakers based on hybrid features[J].Proceedings of the CSEE,2019,39(21):6439-6452.)
• [6]赵书涛，许文杰，李云鹏，等.基于优选泛特征的真空断路器弹簧机构储能状态辨识方法[J].高电压技术，2021,47(11):3777-3784.(Zhao Shutao,Xu Wenjie,Li Yunpeng,et al.Identification method for energy storage state of spring mechanism of vacuum circuitbreaker based on optimal multi-characteristics[J].High Voltage Engineering,2021,47(11):3777-3784.)
• [7]马星光，王晓一，黄锐，等.基于复合特征的GIS振动信号特征提取方法[J].高压电器，2021,57(12):83-89.(Ma Xingguang,Wang Xiaoyi,Huang Rui,et al. Extraction method of GIS vibration signal characteristic based on composite feature[J].High Voltage Apparatus,2021,57(12):83-89.)
• [8]Belgiu M,Dr??gu??L.Random forest in remote sensing:a review of applications and future directions[J].ISPRS Journal of Photogrammetry and Remote Sensing,2016(114):24-31.
• [9]Huang G B,Zhu Q Y,Siew C K.Extreme learning machine:theory and applications[J].Neurocomputing,2016,70(1-3):489-501.
• [10]Steinwart I,Christmann A.Support Vector Machines[M].Springer New York,2008.
• [11]张欣，张静，高旭，等.采用局部时—频奇异值与优化随机森林的高压断路器机械故障诊断[J].高压电器，2020,56(6):225-231.(Zhang Xin,Zhang Jing,Gao Xu,et al.High voltage circuit breaker mechanical fault diagnosis with local time-frequency singular value and the optimal random forest[J].High Voltage Apparatus,2020,56(6):225-231.)
• [12]宋玉琴，王冰，李超，等.基于优化随机森林算法的高压断路器故障诊断[J].电子测量技术，2018,41(21):95-98.(Song Yuqin,Wang Bing,Li Chao,et al.Fault diagnosis of high-voltage circuit breaker based on optimized random forest algorithm[J]. Electronic Measurement Technology,2018,41(21):95-98.)
• [13]Lei Y,He Z,Zi Y,et al.Fault diagnosis of rotating machinery based on multiple ANFIS combination with GAs[J].Mechanical Systems and Signal Processing,2007,21(5):2280-2294.
• [14]Powell G E,Percival I C.A spectral entropy method for distinguishing regular and irregular motion of Hamiltonian systems[J].Journal of Physics A:Mathematical and General,1979,12(11):2053.
• [15]Pan Y N,Chen J,Li X L.Spectral entropy:a complementary index for rolling element bearing performance degradation assessment[J]. Proceedings of the Institution of Mechanical Engineers,Part C:Journal of Mechanical Engineering Science,2009,223(5):1223-1231.
• [16]Stricker M A,Orengo M.Similarity of color images[C].Proceedings of SPIE,The International Society for Optical Engineering,1995(2420):381-392.
• [17]Tamura H,Mori S,Yamawaki T.Textural features corresponding to visual perception[J].IEEE Transactions on Systems,Man,and Cybernetics,1978,8(6):460-473.
• [18]Mirjalili S. The ant lion optimizer[J]. Advances in Engineering Software,2015(83):80-98.
• [19]Wang G,Luo Z,Qin X,et al.Fault identification and classification of rolling element bearing based on time-varying autoregressive spectrum[J].Mechanical Systems and Signal Processing,2008,22(4):934-947.
• [20]Van der Maaten L,Hinton G.Visualizing data using t-SNE[J].Journal of Machine Learning Research,2008,9(11).