| 401 | 0 | 214 |
| 下载次数 | 被引频次 | 阅读次数 |
为实现模块化多电平换流器子模块开路故障诊断，提出一种改进长鼻浣熊优化算法结合最小二乘支持向量机的故障诊断方法。该方法针对长鼻浣熊优化算法的初始化、探索和开发3个阶段分别引入折射反向学习策略、levy飞行策略、螺旋搜索机制和E分布随机扰动，以提升算法的收敛速度和全局搜索能力，并找到最小二乘支持向量机中的惩罚系数Z和核函数参数g的最优组合。首先在Matlab/Simulink中搭建模块化多电平换流器子模块模型，以子模块开路故障条件下的桥臂电流作为输入量，对改进长鼻优化算法优化的最小二乘支持向量机模型与其他优化算法优化的最小二乘支持向量机模型进行对比分析；其次，研究Z和g对模块化多电平换流器子模块故障诊断准确率的影响。结果表明，本文提出的改进长鼻浣熊优化算法优化最小二乘支持向量机的方法在模块化多电平换流器子模块故障诊断准确率最高，且借助智能优化算法进行参数寻优非常高效。
Abstract：To realize the open-circuit fault diagnosis of modular multilevel converter(MMC)sub-module,a fault diagnosis method based on an improved coati optimization algorithm(ICOA)combined with least squares support vector machine(LSSVM)is proposed. Aimedat the three stages of a coati optimization algorithm such as initialization,exploration and development,the refraction reverse learning strategy,levy flight strategy,spiral search mechanism and E-distribution random disturbance are introduced respectively to improve the convergence speed and global search capability of the algorithm,and the optimal combination of penalty coefficient Z and kernel function parameter g in LSSVM are found. First,anMMC sub-module model is built in Matlab/Simulink,and the arm current under the condition of submodule open-circuit fault is used as the input. On this basis,the LSSVM model optimized by ICOA is compared with thoseoptimized by other optimization algorithms. Second,the influences of Z and g on the accuracy of MMC sub-module fault diagnosis arestudied. Results show that the proposed ICOA-LSSVM method has the highest accuracy in MMC submodule fault diagnosis,and it is efficient inoptimizingthe parameters with the help of an intelligent optimization algorithm.
[1]Lesnicar A,Marquardt R. An innovative modular multilevel converter topology suitable for a wide power range[C]//IEEE Bologna Power Tech Conference. Bologna,Italy:IEEE,2003:6-11.
[2]郭铭群，梅念，李探，等（Guo Mingqun,Mei Nian,Li Tan,et al）.±500 kV张北柔性直流电网工程系统设计（System design of±500 kV Zhangbei VSC-based DC grid project）[J].电网技术（Power System Technology）,2021,45(10):4194-4204.
[3]薛英林，徐政，张哲任，等（Xue Yinglin,Xu Zheng,Zhang Zheren,et al）. MMC-HVDC换流器阻抗频率特性分析（Analysis on converter impedance-frequency characteristics of the MMC-HVDC system）[J].中国电机工程学报（Proceedings of the CSEE）,2014,34(24):4040-4048.
[4]Choi U M,Blaabjerg F,Lee K B. Study and handling methods of power IGBT module failures in power electronic converter systems[J]. IEEE Transactionson Power Electronics,2015,30(5):2517-2533.
[5]敬华兵，年晓红，龚芬（Jing Huabing,Nian Xiaohong,Gong Fen）. MMC子模块元件短路故障机理及其新型保护策略（Fault mechanism and novel protection strategy of MMC sub-module component short-circuit）[J].电工技术学报（Transactions of China Electrotechnical Society）,2015,30(3):21-27.
[6]Geng Zhi,Han Minxiao,Khan Z W,et al. Detection and localization strategy for switch open-circuit fault in modular multilevel converters[J]. IEEE Transactions on Power Delivery,2020,35(6):2630-2640.
[7]Richardeau F,Pham T T L. Reliability calculation of multilevel converters:theory and applications[J]. IEEE Transactions on Industrial Electronics,2013,60(10):4225-4233.
[8]Picas R,Zaragoza J,Pou J,et al. Reliable modular multilevel converter fault detection with redundant voltage sensor[J]. IEEE Transactions on Power Electronics,2017,32(1):39-51.
[9]荣飞，朱语博，周诗嘉，等（Rong Fei,Zhu Yubo,Zhou Shijia,et al）.基于子模块电压分组检测的MMC子模块开路故障诊断定位方法（Sub-module open fault diagnosis and location method of MMC based onsub-module voltage packet detection）[J].电力自动化设备（Electric Power Automation Equipment）,2020,40(12):127-133.
[10]Jin Yu,Xiao Qian,Jia Hongjie,et al. A novel detection and localization approach of open-circuit switch fault for the grid-connected modular multilevel converter[J]. IEEE Transactions on Industrial Electronics,2023,70(1):112-124.
[11]Hu Xing,Zhang Jianzhong,Xu Shuai,et al. Detection and location of open-circuit fault for modular multilevel converter[J]. International Journal of Electrical Power and Energy Systems,2020,115:105-125.
[12]Chen Xingxing,Liu Jinjun,Deng Zhifeng,et al. A diagnosis strategy for multiple IGBT open-circuit faults of modular multilevel converters[J]. IEEE Transactions on Power Electronics,2021,36(1):191-203.
[13]杨桢，马子莹，李鑫（Yang Zhen,Ma Ziying,Li Xin）.基于WPD-PCA与GA-BP的MMC子模块故障定位方法研究（Fault location of MMC sub-module based on WPD-PCA and GA-BP）[J].电子测量与仪器学报（Journal of Electronic Measurement and Instrumentation）,2019,33(7):181-187.
[14]魏银图，张旸，温步瀛，等（Wei Yintu,Zhang Yang,Wen Buying,et al）.基于支持向量机的模块化多电平换流器子模块开路故障诊断方法（Open circuit fault diagnosis method for modular multilevel converter submodule based on support vector machine）[J].电气技术（Electrical Engineering）,2023,24(10):1-7.
[15]刘建锋，李志远，周亚茹（Liu Jianfeng,Li Zhiyuan,Zhou Yaru）.基于漏磁场和ICOA-ResNet的变压器绕组早期故障诊断（Transformer windings based on leakage field and ICOA-ResNet early fault diagnosis）[J].电力系统保护与控制（Power System Protection and Control）,2024,52(9):99-110.
[16]樊围国，陈珂翰（Fan Weiguo,Chen Kehan）.基于浣熊算法优化双向长短期记忆网络的碳价预测（Carbon price prediction of bidirectional long short term memory network optimized by coati optimization algorithm）[J].电力科学与工程（Electric Power Science and Engineering）,2023,39(7):34-41.
[17]朱熀秋，沈良瑜（Zhu Yuqiu,Shen Liangyu）.采用改进遗传算法优化LS-SVM逆系统的外转子无铁心无轴承永磁同步发电机解耦控制（Decoupling control of outer rotor coreless bearing less permanent magnet synchronous generator using LS-SVM inverse system optimized by the improved genetic algorithm）[J].中国电机工程学报（Proceedings of the CSEE）,2024,44(5):2037-2046.
[18]高金兰，王天（Gao Jinlan,Wang Tian）.基于VMDIWOA-LSSVM的短期负荷预测（Short-term load forecasting based on VMD-IWOA-LSSVM）[J].吉林大学学报（信息科学版）（Journal of Jilin University(Information Science Edition)）,2021,39(4):430-438.
[19]Kiranyaz S,Gastli A,Ben-Brahim L,et al. Real-time fault detection and identification for MMC using 1-D convolutional neural networks[J]. IEEE Transactions on Industrial Electronics,2019,66(11):8760-8771.——
[20]Deng Fujin,Jin Ming,Liu Chengkai,et al. Switch open-circuit fault localization strategy for MMCs using slidingtime window based features extraction algorithm[J]. IEEE Transactions on Industrial Electronics,2021,68(10):10193-10206.
[21]李智杰，赵铁柱，李昌华，等（Li Zhijie,Zhao Tiezhu,Li Changhua,et al）.融合多策略的改进鹈鹕优化算法（Improved pelican optimization algorithm fused with multistrategy）[J].控制工程（Control Engineering of China）,2023,11(1):1-15.
[22]李荣雨，王颖（Li Rongyu,Wang Ying）.基于莱维飞行的改进粒子群算法（Improved particle swarm optimization based on Levy flights）[J].系统仿真学报（Journal of System Simulation）,2017,29(8):1685-1691,1701.
[23]丁飞，江铭炎（Ding Fei,Jiang Mingyan）.基于改进狮群算法和BP神经网络模型的房价预测（Housing price prediction based on improved lion swarm algorithm and BP neural network model）[J].山东大学学报（工学版）（Journal of Shandong University(Engineering Science)）,2021,51(4):8-16.
[24]刘微，任腾腾，韩广雨，等（Liu Wei,Ren Tengteng,Han Guangyu,et al）.多策略改进蜣螂优化算法及其应用（Multi-strategy improvement of dung beetle optimization algorithm and its application）[J].电子测量技术（Electronic Measurement Technology）,2024,47(12):109-121.
[25]李广强，董文超，朱大庆，等（Li Guangqiang,Dong Wenchao,Zhu Daqing,et al）.基于改进鲸鱼优化算法的AUV三维路径规划（3D path planning for AUV based on improved whale optimization algorithm）[J].系统工程与电子技术（Systems Engineering and Electronics）,2023,45(7):2170-2182.
[26]付雪，朱良宽，黄建平，等（Fu Xue,Zhu Liangkuan,Huang Jianping,et al）.基于改进北方苍鹰优化算法的多阈值图像分割（Multi-threshold image segmentation based on improved northern goshawk optimization algorithm）[J].计算机工程（Computer Engineering）,2023,49(7):232-241.
[27]李斌，高鹏，郭自强（Li Bin,Gao Peng,Guo Ziqiang）.改进蜣螂算法优化LSTM的光伏阵列故障诊断（Improved dung beetle optimizer to optimize LSTM for photovoltaic array fault diagnosis）[J].电力系统及其自动化学报（Proceedings of the CSU-EPSA）,2024,36(8):70-78.
基本信息:
DOI：10.19635/j.cnki.csu-epsa.001625
中图分类号:TM46;TP277
引用信息:
[1]张彼德,汪瑞杰,曾杰,等.改进长鼻浣熊优化最小二乘支持向量机的MMC子模块故障诊断方法[J].电力系统及其自动化学报,2025,37(12):96-105.DOI:10.19635/j.cnki.csu-epsa.001625.
基金信息:
四川省高校重点实验室资助项目（SN240101）
2025-05-07
2025-05-07
2025-05-07