基于IVMD-LSTM的模块化多电平变换器故障诊断

刘述喜; 王乾蕴; 刘科; 曲雨霏; 罗钦

doi:10.19912/j.0254-0096.tynxb.2023-1998

PDF(1783 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (4) : 114-124. DOI: 10.19912/j.0254-0096.tynxb.2023-1998

基于IVMD-LSTM的模块化多电平变换器故障诊断

刘述喜^1,2, 王乾蕴¹, 刘科¹, 曲雨霏¹, 罗钦¹

作者信息 +

FAULT DIAGNOSIS FOR MODULAR MULTILEVEL CONVERTERS BASED ON IVMD-LSTM

Liu Shuxi^1,2, Wang Qianyun¹, Liu Ke¹, Qu Yufei¹, Luo Qin¹

Author information +

文章历史 +

摘要

为提高模块化多电平变换器（MMC）子模块开关管开路故障诊断准确率和效率,提出一种基于改进型变分模态分解的长短期记忆递归神经网络（IVMD-LSTM）的MMC子模块开关管故障诊断方法。该方法直接采用子模块电容电压作为故障特征量,首先通过阿基米德优化算法（AOA）对变分模态分解（VMD）算法进行优化,得到不同样本特征的最优模态分量数量和惩罚因子,对故障样本数据进行模态分解,取特征最显著的3个模态分量组成数据集,然后使用LSTM对故障数据进行分类诊断,得到MMC子模块开关管故障最终诊断结果。仿真结果表明所提方法的分类诊断表现明显优于其他方法,提高了MMC开关管故障诊断准确率和效率,可实现精确、快速、可靠的故障诊断。

Abstract

In order to improve the accuracy and efficiency of open circuit fault diagnosis of modular-multilevel converter （MMC） sub-module switching tube, a new fault diagnosis method of long short-term memory recurrent neural network based on improved variational mode decomposition （IVMD-LSTM） is proposed. In this method, the sub-module capacitor voltage is directly used as the fault characteristic quantity. Firstly, the Archimedes optimization algorithm （AOA） is used to optimize the VMD algorithm to obtain the optimal modal component number and penalty factor of different sample characteristics. Then, the modal decomposition of the fault sample data is carried out, and the three modal components with the most significant characteristics are selected to compose the data set. After that, using LSTM to classifiy the fault data and to obtain the final diagnosis result of MMC sub-module switch tube fault. Simulation results show that the proposed method performs better than other methods, improves the accuracy and efficiency of MMC switching tube fault diagnosis, and can realize accurate, fast and reliable fault diagnosis.

导出引用

刘述喜, 王乾蕴, 刘科, 曲雨霏, 罗钦. 基于IVMD-LSTM的模块化多电平变换器故障诊断[J]. 太阳能学报. 2025, 46(4): 114-124 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1998

Liu Shuxi, Wang Qianyun, Liu Ke, Qu Yufei, Luo Qin. FAULT DIAGNOSIS FOR MODULAR MULTILEVEL CONVERTERS BASED ON IVMD-LSTM[J]. Acta Energiae Solaris Sinica. 2025, 46(4): 114-124 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1998

中图分类号： TM46

参考文献

[1] 曾昭瑢, 何怡刚. 基于SE-DSCNN的MMC开关管故障诊断方法[J]. 电力自动化设备, 2022, 42(5): 104-111.
ZENG Z R, HE Y G.Fault diagnosis method for switches in MMC based on SE-DSCNN[J]. Electric power automation equipment, 2022, 42(5): 104-111.
[2] 荣飞, 朱语博, 周诗嘉, 等. 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[J]. 电力自动化设备, 2020, 40(12): 127-135.
RONG F, ZHU Y B, ZHOU S J, et al.Sub-module open fault diagnosis and location method of MMC based on sub-module voltage packet detection[J]. Electric power automation equipment, 2020, 40(12): 127-135.
[3] 尹桥宣, 段斌, 沈梦君, 等. 模块化五电平逆变器子模块开路故障的智能诊断方法[J]. 电力系统自动化, 2018, 42(12): 127-133, 147.
YIN Q X, DUAN B, SHEN M J, et al.Intelligent diagnosis method for open-circuit fault of sub-modules in modular five-level inverter[J]. Automation of electric power systems, 2018, 42(12): 127-133, 147.
[4] 姚良忠, 吴婧, 王志冰, 等. 未来高压直流电网发展形态分析[J]. 中国电机工程学报, 2014, 34(34): 6007-6020.
YAO L Z, WU J, WANG Z B, et al.Pattern analysis of future HVDC grid development[J]. Proceedings of the CSEE, 2014, 34(34): 6007-6020.
[5] 刘玉林, 齐静静, 李家宁, 等. 一种基于桥臂电流畸变及自适应观测的MMC子模块开路故障诊断定位方法[J]. 电源学报, 2020, 18(3): 106-115.
LIU Y L, QI J J, LI J N, et al.Diagnosis and location method for open-circuit fault in MMC sub-module based on bridge arm current distortion and adaptive observation[J]. Journal of power supply, 2020, 18(3): 106-115.
[6] 杨贺雅, 邢纹硕, 陈聪, 等. 基于随机森林二分类器的模块化多电平换流器子模块开路故障检测方法[J]. 中国电机工程学报, 2023, 43(10): 3916-3928.
YANG H Y, XING W S, CHEN C, et al.A fault detection and location strategy for sub-module open-circuit fault in modular multilevel converters based on random forest binary classifier[J]. Proceedings of the CSEE, 2023, 43(10): 3916-3928.
[7] 杨贺雅, 邢纹硕, 向鑫, 等. 基于多元高斯分布异常检测模型的MMC子模块开路故障诊断方法[J]. 电工技术学报, 2023, 38(10): 2744-2756.
YANG H Y, XING W S, XIANG X, et al.A sub-module open-circuit fault detection and location strategy for modular multilevel converters based on multivariate Gaussian distribution[J]. Transactions of China Electrotechnical Society, 2023, 38(10): 2744-2756.
[8] 徐坤山, 谢少军, 袁小峰, 等. 模块化多电平换流器子模块故障快速诊断方法[J]. 电力系统自动化, 2017, 41(18): 103-110.
XU K S, XIE S J, YUAN X F, et al.Rapid diagnostic method for submodule failure in modular multilevel converter[J]. Automation of electric power systems, 2017, 41(18): 103-110.
[9] BENTO F, MARQUES CARDOSO A J. A comprehensive survey on fault diagnosis and fault tolerance of DC-DC converters[J]. Chinese journal of electrical engineering, 2018, 4(3): 1-12.
[10] 武鸿, 王跃, 刘熠, 等. 基于全桥型MMC的开关序列切换方法及IGBT开路故障诊断策略[J]. 高电压技术, 2024, 50(4): 1608-1620.
WU H, WANG Y, LIU Y, et al.A switching sequence switching method and IGBT open circuit fault diagnosis strategy for full-bridge MMC[J]. High voltage engineering, 2024, 50(4): 1608-1620.
[11] LIU C K, DENG F J, CAI X, et al.Submodule open-circuit fault detection for modular multilevel converters under light load condition with rearranged bleeding resistor circuit[J]. IEEE transactions on power electronics, 2022, 37(4): 4600-4613.
[12] 武鸿, 王跃, 刘熠, 等. 基于广义电容电压不平衡度的MMC子模块开路故障诊断策略[J]. 电工技术学报, 2023, 38(14): 3909-3922.
WU H, WANG Y, LIU Y, et al.Open circuit fault diagnosis strategy of MMC sub-module based on generalized capacitor voltage unbalance[J]. Transactions of China Electrotechnical Society, 2023, 38(14): 3909-3922.
[13] 孔令瑜, 张彼德, 洪锡文, 等. MMC五电平逆变器故障的深度小波极限学习机诊断方法研究[J]. 电力系统及其自动化学报, 2020, 32(7): 25-32.
KONG L Y, ZHANG B D, HONG X W, et al.Study on fault diagnosis method for MMC five-level inverter based on DWELM[J]. Proceedings of the CSU-EPSA, 2020, 32(7): 25-32.
[14] 唐志军, 周刚, 晁武杰, 等. 基于多分类相关向量机的MMC多相故障诊断关键技术[J]. 电力系统保护与控制, 2021, 49(16): 112-118.
TANG Z J, ZHOU G, CHAO W J, et al.Key technologies of MMC multiphase fault diagnosis based on a multi class correlation vector machine[J]. Power system protection and control, 2021, 49(16): 112-118.
[15] WANG T Z, XU H, HAN J G, et al.Cascaded H-bridge multilevel inverter system fault diagnosis using a PCA and multiclass relevance vector machine approach[J]. IEEE transactions on power electronics, 2015, 30(12): 7006-7018.
[16] 林亮行, 马国政, 孙建芳, 等. 基于VMD-EEMD-LSTM的涂层型关节轴承剩余使用寿命预测方法[J]. 机械工程学报, 2023, 59(9): 125-136.
LIN L X, MA G Z, SUN J F, et al.Remaining useful life prediction method of coated spherical plain bearing based on VMD-EEMD-LSTM[J]. Journal of mechanical engineering, 2023, 59(9): 125-136.
[17] 曹洁, 张玉林, 王进花, 等. 基于VMD和SVPSO-BP的滚动轴承故障诊断[J]. 太阳能学报, 2022, 43(9): 294-301.
CAO J, ZHANG Y L, WANG J H, et al.Fault diagnosis of rolling bearing based on VMD and SVPSO-BP[J]. Acta energiae solaris sinica, 2022, 43(9): 294-301.
[18] 张琰妮, 史加荣, 李津, 等. 融合残差与VMD-ELM-LSTM的短期风速预测[J]. 太阳能学报, 2023, 44(9): 340-347.
ZHANG Y N, SHI J R, LI J, et al.Short-term wind speed prediction based on residual and VMD-ELM-LSTM[J]. Acta energiae solaris sinica, 2023, 44(9): 340-347.
[19] 梁智, 孙国强, 李虎成, 等. 基于VMD与PSO优化深度信念网络的短期负荷预测[J]. 电网技术, 2018, 42(2): 598-606.
LIANG Z, SUN G Q, LI H C, et al.Short-term load forecasting based on VMD and PSO optimized deep belief network[J]. Power system technology, 2018, 42(2): 598-606.
[20] 王宏伟, 孙文磊, 张小栋, 等. 基于优化VMD复合多尺度散布熵及LSTM的风力发电机齿轮箱故障诊断方法研究[J]. 太阳能学报, 2022, 43(4): 288-295.
WANG H W, SUN W L, ZHANG X D, et al.Fault diagnosis method of wind turbine’s gearbox based on composite multiscale dispersion entropy of optimised VMD and LSTM[J]. Acta energiae solaris sinica, 2022, 43(4): 288-295.
[21] DRAGOMIRETSKIY K, ZOSSO D.Variational mode decomposition[J]. IEEE transactions on signal processing, 2014, 62(3): 531-544.
[22] HASHIM F A, HUSSAIN K, HOUSSEIN E H, et al.Archimedes optimization algorithm: a new metaheuristic algorithm for solving optimization problems[J]. Applied intelligence, 2021, 51(3): 1531-1551.
[23] 唐贵基, 王晓龙. 参数优化变分模态分解方法在滚动轴承早期故障诊断中的应用[J]. 西安交通大学学报, 2015, 49(5): 73-81.
TANG G J, WANG X L.Parameter optimized variational mode decomposition method with application to incipient fault diagnosis of rolling bearing[J]. Journal of Xi’an Jiaotong University, 2015, 49(5): 73-81.
[24] HOCHREITER S, SCHMIDHUBER J.Long short-term memory[J]. Neural computation, 1997, 9: 1735-1780.
[25] GERS F A, SCHMIDHUBER J, CUMMINS F.Learning to forget: continual prediction with LSTM[J]. Neural computation, 2000, 12(10): 2451-2471.
[26] 王福忠, 王帅峰, 张丽. 基于VMD-LSTM与误差补偿的光伏发电超短期功率预测[J]. 太阳能学报, 2022, 43(8): 96-103.
WANG F Z, WANG S F, ZHANG L.Ultra short term power prediction of photovoltaic power generation based on VMD-LSTM and error compensation[J]. Acta energiae solaris sinica, 2022, 43(8): 96-103.
[27] 赵成勇, 胡静, 翟晓萌, 等. 模块化多电平换流器桥臂电抗器参数设计方法[J]. 电力系统自动化, 2013, 37(15): 89-94.
ZHAO C Y, HU J, ZHAI X M, et al.A parameter design method of bridge arm reactor in modular multilevel converter[J]. Automation of electric power systems, 2013, 37(15): 89-94.
[28] 徐政, 肖晃庆, 张哲任. 模块化多电平换流器主回路参数设计[J]. 高电压技术, 2015, 41(8): 2514-2527.
XU Z, XIAO H Q, ZHANG Z R.Design of main circuit parameters of modular multilevel converters[J]. High voltage engineering, 2015, 41(8): 2514-2527.