[1]张跃,梁智明,胡波,等.采用混合核函数支持向量机算法的大型发电机定子线棒绝缘状态评估方法[J].西安交通大学学报,2020,54(06):044-50.[doi:10.7652/xjtuxb202006006]
 ZHANG Yue,LIANG Zhiming,HU Bo,et al.An Evaluation Method for Insulation State of Large Generator Stator Bar Based on Support Vector Machine with Hybrid Kernel Function[J].Journal of Xi'an Jiaotong University,2020,54(06):044-50.[doi:10.7652/xjtuxb202006006]
点击复制

采用混合核函数支持向量机算法的大型发电机定子线棒绝缘状态评估方法
分享到:

《西安交通大学学报》[ISSN:0253-987X/CN:61-1069/T]

卷:
54
期数:
2020年第06期
页码:
044-50
栏目:
出版日期:
2020-06-10

文章信息/Info

Title:
An Evaluation Method for Insulation State of Large Generator Stator Bar Based on Support Vector Machine with Hybrid Kernel Function
文章编号:
0253-987X(2020)06-0044-07
作者:
张跃1 梁智明1 胡波1 张莹2 李志成2 刘凌2
1.东方电气集团东方电机有限公司, 618000, 四川德阳; 2.西安交通大学电气工程学院, 710049, 西安
Author(s):
ZHANG Yue1 LIANG Zhiming1 HU Bo1 ZHANG Ying2 LI Zhicheng2 LIU Ling2
1. Dongfang Electric Machinery Co. Ltd., Deyang, Sichuan 618000, China; 2. School of Electrical Engineering, Xi’an Jiaotong University, Xi’an 710049, China
关键词:
发电机 定子线棒 非破坏性特征参量 支持向量机 状态评估
Keywords:
generator stator bar non-destructive parameters support vector machine
分类号:
TM31
DOI:
10.7652/xjtuxb202006006
文献标志码:
A
摘要:
为解决大容量发电机定子线棒的绝缘状态难以评估的问题,提出了一种采用混合核函数支持向量机算法的大型发电机定子线棒绝缘状态评估方法。该方法根据多因子老化试验平台,得到能表征定子线棒绝缘老化状态的非破坏性特征参量如吸收比、介质损耗、介损增量等在不同周期下的数值,并通过计算皮尔逊相关系数进一步验证上述非破坏性参量在数值上与剩余击穿场强的显著相关性; 然后采用混合核函数支持向量机算法建立定子线棒非破坏性特征参量与剩余击穿场强的映射关系模型,预测出定子线棒剩余击穿场强; 最后结合层次分析法及上述支持向量机算法的预测结果实现了对发电机定子主绝缘状态的评估。数值仿真结果表明:与传统单核函数支持向量机预测算法相比,基于混合核函数支持向量机和层次分析法的评估方法弥补了单核核函数预测结果不收敛的缺陷,对剩余击穿场强的识别准确率达到97%,该方法表现出了较强的状态评估能力。
Abstract:
A method using a support vector machine algorithm with hybrid kernel function is proposed to solve the problem that it is difficult to evaluate the insulation status of stator bars of large-capacity generators. The method bases on a multi-factor aging test platform to obtain non-destructive characteristic parameters such as absorption ratio, dielectric loss, and dielectric loss increment at different periods that can characterize the insulation aging state of a stator bar. Pearson correlation coefficient is calculated to further verify the significant correlation between the above non-destructive parameters and the residual breakdown field strength. Then the support vector machine algorithm with hybrid kernel function is used to establish the mapping relationship between the non-destructive characteristic parameters of the stator bar and the residual breakdown field strength and to predict the residual breakdown field strength of the stator bar. Finally, the main insulation state of the generator stator is evaluated by the analytic hierarchy process and prediction results based on the support vector machine algorithm. Numerical simulation results and a comparison with the traditional single-kernel function support vector machine algorithm show that the algorithm based on the proposed support vector machine and the analytic hierarchy process makes up the shortcoming that the prediction results of the single-core kernel function do not converge, and the recognition accuracy of breakdown field strength reaches 97%. The method shows a strong state assessment ability.

参考文献/References:

[1] 乐波, 宋建成. 电机定子线圈绝缘多因子老化特征的研究 [J]. 高电压技术, 2000, 26(2): 3-7.
LE Bo, SONG Jiancheng. Research on multi-factor aging characteristics of motor stator coil insulation [J]. High Voltage Engineering, 2000, 26(2): 3-7.
[2] 欧阳本红, 刘丽兵, 江裕熬, 等. 发电机定子绝缘剩余寿命评估参量的选择 [J]. 高电压技术, 2005, 31(1): 30-32.
OUYANG Benhong, LIU Libing, JIANG Yuao, et al. Selection of evaluation parameters for residual life of generator stator insulation [J]. High Voltage Engineering, 2005, 31(1): 30-32.
[3] 郝艳捧, 谢恒堃. 基于热重和红外光谱分析研究大电机定子绝缘中环氧的老化过程 [J]. 中国电机工程学报, 2008, 28(13): 15-19.
HAO Yanpeng, XIE Hengkun. Study on the aging process of epoxy in large motor stator insulation based on thermogravimetry and infrared spectroscopy [J]. Proceedings of the CSEE, 2008, 28(13): 15-19.
[4] 郝艳捧, 谢恒堃. 红外光谱法研究运行23年大电机定子绝缘中环氧的老化机理 [J]. 电工技术学报, 2008, 23(3): 19-23.
HAO Yanpeng, XIE Hengkun. Infrared spectroscopy study on the aging mechanism of epoxy in stator insulation of 23 years old motor [J]. Transactions of China Electrotechnical Society, 2008, 23(3): 19-23.
[5] 宋建成, 成永红, 高乃奎, 等. 基于动态力学分析的大电机主绝缘老化诊断 [J]. 中国电机工程学报, 2005, 25(2): 99-104.
SONG Jiancheng, CHENG Yonghong, GAO Naikui, et al. Aging diagnosis of large motor main insulation based on dynamic mechanical analysis [J]. Proceedings of the CSEE, 2005, 25(2): 99-104.
[6] HAO Yanpeng, XIE Hengkun. WANG Guoli, et al. Assessment of insulation condition of generator stator bars based on velocity of ultrasonic waves [J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2003, 10(3): 539-547.
[7] 郝艳捧, 谢恒堃, 王国利, 等. 用超声波波速评估大电机主绝缘的剩余运行年数 [J]. 中国电机工程学报, 2005, 25(4): 76-82.
HAO Yanpeng, XIE Hengkun, WANG Guoli, et al. Evaluation of the remaining years of operation of main motor main insulation using ultrasonic wave velocity [J]. Proceedings of the CSEE, 2005, 25(4): 76-82.
[8] 乐波, 李俭, 闫波, 等. 用最大放电量增加率评定定子绝缘老化状态 [J]. 高电压技术, 2001, 27(1): 1-3.
LE Bo, LI Jian, YAN Bo, et al. Stator insulation aging condition is evaluated by the maximum discharge rate increase rate [J]. High Voltage Engineering, 2001, 27(1): 1-3.
[9] 乐波, 成永红, 陈小林, 等. 基于人工智能的大电机主绝缘老化状态评估软件 [J]. 电力系统自动化, 2005, 29(14): 78-82.
LE Bo, CHENG Yonghong, CHEN Xiaolin, et al. Large-scale motor main insulation aging state evaluation software based on artificial intelligence [J]. Automation of Electric Power Systems, 2005, 29(14): 78-82.
[10] 郝艳捧, 王国利, 闫波, 等. 大电机定子线棒绝缘状态诊断的研究进展 [J]. 高电压技术, 2001, 27(1): 4-6.
HAO Yanpeng, WANG Guoli, YAN Bo, et al. Research progress on insulation state diagnosis of large motor stator bars [J], High Voltage Engineering, 2001, 27(1): 4-6.
[11] LAMARRE L, DAVID E. Temperature dependence of the resistance of modern epoxy mica insulation of HV rotating machines [J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2008, 15(5): 1305-1312.
[12] 闫富松, 李朝晖. 一种基于皮尔逊相关系数识别变压器励磁涌流的方法 [J]. 高压电器, 2016, 52(8): 52-56.
YAN Fusong, LI Chaohui. A method for identifying transformer inrush current based on Pearson correlation coefficient [J]. High Voltage Apparatus, 2016, 52(8): 52-56.
[13] 王涓, 吴旭鸣, 王爱凤. 应用皮尔逊相关系数算法查找异常电能表用户 [J]. 电力需求侧管理, 2014, 16(2): 57-59.
WANG Juan, WU Xuming, WANG Aifeng. Application of Pearson correlation coefficient algorithm to find abnormal energy meter users [J]. Power Demand Side Management, 2014, 16(2): 57-59.
[14] 周志华. 机器学习 [M]. 北京: 清华大学出版社, 2016: 121-139, 298-300.
[15] 司刚全, 李水旺, 石建全, 等. 采用改进果蝇优化算法的最小二乘支持向量机参数优化方法 [J]. 西安交通大学学报, 2017, 51(6): 14-19.
SI Gangquan, LI Shuiwang, SHI Jianquan, et al. Least squares support vector machine parameters optimization based on improved fruit fly optimization algorithm with applications [J]. Journal of Xi’an Jiaotong University, 2017, 51(6): 14-19.
[16] 吴建宁, 王珏. 采用支持向量机评估老年人步态对称性的研究 [J]. 西安交通大学学报, 2007, 41(8): 995-999.
WU Jianning, WANG Jue. Evaluation of the gait symmetry of old people using support vector machine [J]. Journal of Xi’an Jiaotong University, 2007, 41(8): 995-999.
[17] 许树柏. 实用决策方法: 层次分析法原理 [M]. 天津: 天津大学出版社, 1988: 46-52.
[18] 郭金玉, 张忠彬, 孙庆云. 层次分析法的研究与应用 [J]. 中国安全科学学报, 2008, 18(5): 148-153.
GUO Jinyu, ZhANG Zhongbin, SUN Qingyun. Research and application of analytic hierarchy process [J]. Chinese Journal of Safety Science, 2008, 18(5): 148-153.
[19] 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. On statistical learning theory and support vector machines [J]. Acta Automatica Sinica, 2000, 26(1): 32-42.
[20] 刘小生, 章治邦. 基于改进网格搜索法的SVM参数优化 [J]. 江西理工大学学报, 2019, 40(1): 5-9.
LIU Xiaosheng, ZHANG Zhibang. SVM parameter optimization based on improved grid search method [J]. Journal of Jiangxi University of Science and Technology, 2019, 40(1): 5-9.

备注/Memo

备注/Memo:
收稿日期: 2019-12-25。 作者简介: 张跃(1982—),男,博士,高级工程师; 刘凌(通信作者),男,博士,副教授,博士生导师。 基金项目: 国家自然科学基金资助项目(51977173)。
更新日期/Last Update: 2020-06-10