[1]刘 伟,韩彦华,王 荆,等.基于粒子群算法优化支持向量机的变压器绕组变形分类方法[J].高压电器,2020,56(03):72-78.[doi:10.13296/j.1001-1609.hva.2020.03.011]
 LIU Wei,HAN Yanhua,WANG Jing,et al.Transformer Winding Deformation Classification Method Based on Particle Swarm Algorithm Optimizing Support Vector Machine[J].High Voltage Apparatus,2020,56(03):72-78.[doi:10.13296/j.1001-1609.hva.2020.03.011]
点击复制

基于粒子群算法优化支持向量机的变压器绕组变形分类方法()
分享到:

《高压电器》[ISSN:1001-1609/CN:61-11271/TM]

卷:
第56卷
期数:
2020年03期
页码:
72-78
栏目:
研究与分析
出版日期:
2020-03-15

文章信息/Info

Title:
Transformer Winding Deformation Classification Method Based on Particle Swarm Algorithm Optimizing Support Vector Machine
作者:
刘 伟1 韩彦华2 王 荆2 刘江南3 赵仲勇3
(1. 国网陕西省电力公司, 西安 710048; 2. 国网陕西省电力公司电力科学研究院, 西安 710100; 3. 西南大学工程技术学院, 重庆 400716)
Author(s):
LIU Wei1 HAN Yanhua2 WANG Jing2 LIU Jiangnan3 ZHAO Zhongyong3
(1. State Grid Shaanxi Electric Power Company, Xi’an 710048, China; 2. State Grid Shanxi Electric Power Research Institute, Xi’an 710100, China; 3. College of Engineering and Technology, Southwest University, Chongqing 400716, China)
关键词:
变压器 故障诊断 频率响应 支持向量机 粒子群算法
Keywords:
transformer fault diagnosis frequency response support vector machine particle swarm algorithm
DOI:
10.13296/j.1001-1609.hva.2020.03.011
摘要:
变压器是电网最为核心的设备,绕组变形是变压器主要的故障类型之一,频率响应分析法(frequency response analysis, FRA)是目前广泛应用的绕组变形检测方法。为提高绕组变形分类诊断的性能,文中提出基于粒子群算法优化支持向量机(particle swarm optimization?support vector machine, PSO-SVM)的变压器绕组变形分类方法,采用数学统计方法提取频率响应曲线的特征参量,并输入到支持向量机模型进行训练,利用粒子群算法优化支持向量机模型参数,使其能够有效区分不同的绕组故障类型。为证明文中方法在变压器绕组故障诊断方面的有效性,在一台特制模型变压器上进行了一系列故障模拟实验。数据处理结果表明,训练后的支持向量模型表现出了极高的性能,并且,相比传统的网格搜索参数优化算法,粒子群算法优化的支持向量机可以显著提高变压器绕组变形故障的分类性能。
Abstract:
Transformer is the core equipment of power grid, winding deformation is one of transformer common faults, and frequency response analysis is a widely used winding deformation detection method. In order to improve the performance of classifying and diagnosing winding deformation, this paper proposes a transformer winding deformation classification method based on particle swarm algorithm optimizing support vector machine, the mathematical statistical method is used to extract the characteristic parameters of frequency response curves, which are imported into SVM model to perform the training. The particle swarm algorithm is used to optimize the parameters of SVM model, to effectively distinguish variable winding fault types. In order to prove the effectiveness of the presented method in diagnosing transformer winding faults, a series of fault emulating experiments are carried out on a specially manufactured model transformer. The data process result indicates that the SVM model after training presents high performance; moreover, compared to the traditional grid searching parameter optimization method, the SVM which is optimized by particle swarm algorithm can remarkably improve the performance of classifying transformer winding deformation faults.

参考文献/References:

[1] 陈嘉宁,杨 翾,叶承晋,等. 基于缺失数据修复的变压器在线故障诊断方法[J]. 电力系统保护与控制,2019,47(15): 86-92. CHEN Jianing,YANG Xuan,YE Chengjin,et al. On-line fault diagnosis method for power transformer based on missing data repair[J]. Power System Protection and Control,2019,47(15): 86-92.
[2] 赵仲勇,唐 超,李成祥,等. 基于频率响应二值化图像的变压器绕组变形故障诊断方法[J]. 高电压技术,2019,45(5):1526-1534. ZHAO Zhongyong,TANG Chao,LI Chengxiang,et al. Diagnosis method of transformer winding deformation faults based on frequency response binary image[J]. High Voltage Engineering,2019,45(5): 1526-1534.
[3] 陈 程,聂德鑫,冯振新,等. 基于概率输出支持向量机和证据理论的变压器故障诊断技术[J]. 变压器,2018,55(7):58-61. CHEN Cheng,NIE Dexin,FENG Zhenxin,et al. Fault diagnosis technology of power transformer using probability output of SVM and DS theory[J]. Transformer,2018,55(7): 58-61.
[4] 姚陈果,赵仲勇,李成祥,等. 基于暂态过电压特性的电力变压器绕组变形故障在线检测[J]. 高电压技术,2015,41(3):873-880. YAO Chenguo,ZHAO Zhongyong,LI Chengxiang,et al. Online detecting winding deformation of power transformer based on transient overvoltage[J]. High Voltage Engineering,2015,41(3): 873-880.
[5] 刘云鹏,程槐号,胡 焕,等. 基于频响曲线稀疏表示的变压器绕组变形模式识别方法[J]. 电测与仪表,2018,55(5):14-21. LIU Yunpeng,CHENG Huaihao,HU Huan,et al. A transformer winding deformation pattern recognition method based on sparse representation of frequency response curve[J]. Electrical Measurement & Instrumentation,2018,55(5): 14-21.
[6] PORTILLA W H,MAYOR- G A,GUERRA J P,et al. Detection of transformer faults using frequency-response traces in the low-frequency bandwidth[J]. IEEE Transactions on Industrial Electronics,2014,61(9):4971-4978.
[7] 杨强令. 电力变压器绕组状态检测技术应用现状[J]. 通信电源技术,2019,36(2):138-139. YANG Qiangling. Application status of power transformer winding state detection technology[J]. Telecom Power Technology,2019,36(2): 138-139.
[8] ABU-SIADA A,HASHEMNIA N,ISLAM S,et al. Understanding power transformer frequency response analysis signatures[J]. IEEE Electrical Insulation Magazine,2013,29(3):48-56.
[9] LIU J,ZHAO Z,TANG C,et al. Classifying transformer winding deformation fault types and degrees using FRA based on support vector machine[J]. IEEE ACCESS,2019(7):112494-112504.
[10] 田晓飞. 基于改进蝙蝠算法优化支持向量机的变压器故障诊断研究[J]. 黑龙江电力,2019,41(01):11-15. TIAN Xiaofei. Research on transformer fault diagnosis based on improved bat algorithm optimizing support vector machine[J]. Heilongjiang Electric Power,2019,41(1): 11-15.
[11] 谷红霞,黄志华. 基于SVM的电力变压器绕组变形类型识别[J]. 内燃机与配件,2018(13):131-134. GU Hongxia,HUANG Zhihua. The recognition of power transformer winding deformation type based on SVM[J]. Internal Combustion Engine & Parts,2018(13): 131-134.
[12] 陈晓晗. 基于有限元法的电力变压器绕组变形检测与识别的仿真研究[D]. 重庆:重庆大学,2015. CHEN Xiaohan. Simulation study on monitoring and recognition power transformer winding deformation based on finite element method[D]. Chongqing :Chongqing University,2015.
[13] 欧阳旭东,林春耀,杨 贤,等. 扫频阻抗法检测变压器绕组轴向位移研究[J]. 绝缘材料,2016,49(8):78-81. OUYANG Xudong,LIN Chunyao,YANG Xian,et al. Research on axial displacement detection of transformer winding based on sweep frequency impedance[J]. Insulating Materials,2016,49(8): 78-81.
[14] 司马莉萍. 基于改进支持向量机的电力变压器故障诊断与预测方法的研究[D]. 武汉:武汉大学,2012. SIMA Liping. Research on methods of fault diagnosis and prognosis for power transformer based on improved support vector machines[D]. Wuhan:Wuhan University,2012.
[15] 田凤兰,张恩泽,潘思蓉,等. 基于特征量优选与ICA-SVM的变压器故障诊断模型[J]. 电力系统保护与控制,2019,47(17):163-170. TIAN Fenglan,ZHANG Enze,PAN Sirong,et al. Fault diagnosis model of power transformers based on feature quantity optimization and ICA-SVM[J]. Power System Protection and Control,2019,47(17): 163-170.
[16] 朱超岩,姚晓东. 基于遗传算法优化的支持向量机在变压器故障诊断中应用[J]. 仪表技术,2019(3):21-23. ZHU Chaoyan,YAO Xiaodong. Application of the support vector machine in the fault diagnosis on the transformer based on the optimal genetic algorithm[J]. Instrumentation Technology,2019(3): 21-23.
[17] 杨景刚,吴 越,赵 科,等. 基于最优特征向量分类的高压断路器机械状态识别方法[J]. 高压电器,2018,54(6): 60-66. YANG Jinggang,WU Yue,ZHAO Ke,et al. Mechanical status identification of high voltage circuit breakers based on optimal feature vector classification[J]. High Voltage Apparatus,2018,54(6): 60-66.
[18] 张 琳,马宏忠,姜 宁,等. 基于奇异谱熵和支持向量机的变压器绕组松动识别及定位[J]. 电力系统保护与控制,2017,45(18):69-75. ZHANG Lin,MA Hongzhong,JIANG Ning,et al. Recognition and location of transformer winding looseness based on singular value spectrum entropy and SVM[J]. Power System Protection and Control,2017,45(18): 69-75.
[19] 张 青,赵黎明,焦尚彬. 基于PSO-SVM的高压绝缘子污秽等级评定[J]. 高压电器,2008,44(6):562-565. ZHANG Qing,ZHAO Liming,JIAO Shangbin. Assessment of contamination grades for high voltage insulator based on PSO-SVM[J]. High Voltage Apparatus,2008,44(6): 562-565.
[20] SHI Y H,EBERHART R C. A modified particle swarm optimizer[C]//IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360). [S.l.]:IEEE,1998:69-73.
[21] ZHAO Z,TANG C,ZHOU Q,et al. Identification of power transformerwinding mechanical fault types based on online IFRA by support vector machine[J]. Energies,2017,10(12):2022.
[22] ZHAO Z,TANG C,YAO C,et al. Improved method to obtain the online impulse frequency response signature of a power transformer by multi scale complex CWT[J]. IEEE Access,2018(6):48934-48945.
[23] ZHAO Z,YAO C,LI C,et al. Detection of power transformer winding deformation using improved FRA based on binary morphology and extreme point variation[J]. IEEE Transactions on Industrial Electronics,2018,65(4):3509-3519.

备注/Memo

备注/Memo:
收稿日期:2019-11-12; 修回日期:2020-01-14 基金项目:国家电网公司科技项目(SGTYHT/17-JS-201);国家自然科学基金项目(51807166)。 Project Supported by State Grid Corporation Science and Technology Project(SGTYHT/17-JS-201), the National Natural Science Foundation of China(51807166).刘 伟(1977—),男,硕士,高级工程师,主要从事状态检修、状态监测、电网电能质量应用研究工作。 韩彦华(1974—),男,硕士,教授级高工,主要从事电气设备状态评估及故障诊断技术研究工作。 王 荆(1981—),男,博士,高级工程师,主要从事电气设备状态评估及故障诊断技术研究工作。 赵仲勇(1988—),男,博士,副教授,主要从事电气设备状态评估及故障诊断技术、脉冲功率技术的研究工作。
更新日期/Last Update: 2020-03-15