基于CGAN与LSTM的逆变器多类型故障诊断方法研究

doi:10.3969/j.issn.1008-0198.2023.06.023

湖南电力 ›› 2023, Vol. 43 ›› Issue (6): 151-158.doi: 10.3969/j.issn.1008-0198.2023.06.023

• 故障与分析 • 上一篇

基于CGAN与LSTM的逆变器多类型故障诊断方法研究

田睿¹, 刘维可², 伍珣³, 张晓敏¹

1.国网湖南省电力有限公司超高压变电公司,湖南长沙 410004;
2.国网湖南省电力有限公司电力科学研究院,湖南长沙 410208;
3.中南大学交通运输工程学院,湖南长沙 410075

收稿日期:2023-08-03 修回日期:2023-08-30 出版日期:2023-12-25 发布日期:2024-01-07
通信作者: 田睿(1992),女,工程师,主要从事电气设备状态监测与故障诊断研究工作。
基金资助:
湖南省自然科学基金项目(2023JJ40750)

Multi-Fault Analysis and Diagnosis of Inverters Based on CGAN and LSTM

TIAN Rui¹, LIU Weike², WU Xun³, ZHANG Xiaomin¹

1. State Grid Hunan Extra High Voltage Substation Company, Changsha 410004, China;
2. State Grid Hunan Electric Power Company Research Institute, Changsha 410208, China;
3. School of Transportation and Engineering, Central South University, Changsha 410075, China

Received:2023-08-03 Revised:2023-08-30 Online:2023-12-25 Published:2024-01-07

摘要/Abstract

摘要： 逆变器广泛应用于不间断电源、电机调速及可再生能源并网发电系统,其安全、可靠运行对于变流系统具有重要意义。在恶劣工作环境下,逆变器的功率管与电流传感器极易发生故障,两者故障类型较多且特征相似,给现有的逆变器故障诊断技术带来了极大挑战。针对逆变器多类型故障诊断问题,提出基于时间序列的条件生成对抗网络(conditional generative adversarial network,CGAN)与长短期记忆网络(long short-term memory,LSTM)的故障诊断方法。首先,分析两电平逆变器的基本工作原理,并在dSPACE半实物平台建立基于闭环控制的逆变器数字模型;接着,通过数字模型对单个功率管开路故障、两个功率管开路故障及电流传感器零输出等故障下的工作模态进行探究;在此基础上,以输出电流为监测变量,采用CGAN获取接近真实工况的故障数据集,通过LSTM对功率管与电流传感器故障进行诊断与定位。实验数据表明,该方法能够有效辨别逆变器多类型故障。

关键词: 逆变器, 功率管, 电流传感器, 故障诊断

Abstract: Inverter is widely used in UPS, motors, and renewable energy generation systems. Its safe operation is of great significance for converter systems. In harsh working environments, the power transistor and current sensor of grid connected inverter are prone to faults, and their fault characteristics are similar and coupled, posing great challenges to existing inverter fault diagnosis technologies. Therefore, this paper proposes a coupling fault diagnosis method based on conditional generative adversarial network(CGAN)and long short-term memory(LSTM)for inverters. First, the basic working principle of the inverter is analyzed and a digital model is established on the dSPACE platform. Next, the working modes under single power transistor open circuit fault, double power transistor open circuit faults and zero output fault of the current sensor are explored through the model. Then, three phase currents are used as diagnosis variables, and CGAN is utilized to obtain the fault data which is closed to the real operation conditions. The faults of switches and sensors are finally located by the LSTM network. The experimental data proves the effectiveness of this method.

Key words: inverter, power transistor, current sensor, fault diagnosis

中图分类号:

TM464

田睿, 刘维可, 伍珣, 张晓敏. 基于CGAN与LSTM的逆变器多类型故障诊断方法研究[J]. 湖南电力, 2023, 43(6): 151-158.

TIAN Rui, LIU Weike, WU Xun, ZHANG Xiaomin. Multi-Fault Analysis and Diagnosis of Inverters Based on CGAN and LSTM[J]. Hunan Electric Power, 2023, 43(6): 151-158.

参考文献

[1]WU X,CHEN C Y,CHEN T F,et al. A fast and robust diagnostic method for multiple open-circuit faults of voltage-source inverters through line voltage magnitudes analysis[J]. IEEE Transactions on Power Electronics, 2020,35(5): 5205-5220.
[2]伍珣, 陈特放, 成庶,等. 基于输出电流轨迹的机车逆变器开路故障在线诊断方法[J]. 电工技术学报, 2017, 32(S2): 87-95.
[3]WU X,TIAN R,CHENG S,et al. A nonintrusive diagnostic method for open-circuit faults of locomotive inverters based on output current trajectory[J]. IEEE Transactions on Power Electronics, 2018, 33(5): 4328-4341.
[4]YONG Y,WANG Z, XU D,et al.D. Speed and current sensors fault detection and isolation based on adaptive observers for induction motor drives[J]. Journal of Power Electronics, 2014, 14(5): 967-979.
[5]JLASSI I, ESTIMA J, EL KHIL S, et al. A robust observer-based method forIGBTs and current sensors fault diagnosis in voltage-source inverters of PMSM drives[J]. IEEE Transactions on Industry Applications, 2017, 53(3): 2894-2905.
[6]CHOI C,LEE K,LE W. Observer-based phase-shift fault detection using adaptive threshold for rotor position sensor of permanent-magnet synchronous machine drives in electromechanical brake[J]. IEEE Transactions on Industrial Electronics, 2015, 62(3): 1964-1974.
[7]YOUSSEF A, EL-KHIL S, SLAMA-BELKHODJA I. State observer-based sensor fault detection and isolation, and fault tolerant control of a single-phase PWM rectifier for electric railway traction[J].IEEE Transactions on Power Electronics, 2013, 28(12): 5842-5853.
[8]DONG X, GE X. A state estimator-based approach for open-circuit fault diagnosis in single-phase cascaded H-bridge rectifiers[J].IEEE Transactions on Industry Applications, 2019, 55(2): 1608-1618.
[9]JUNG S, PARK J, KIM H, et al. An MRAS-based diagnosis of open-circuit fault in PWM voltage source inverters for PM synchronous motor drive systems[J]. IEEE Transactions on Power Electronics, 2013, 28(5): 2514-2526.
[10]殷实,谭国俊.一种基于扩展卡尔曼滤波算法的 MMC 系统故障诊断策略[J].电工技术学报, 2016, 31(19): 74-84.
[11]ZHANG X, GILBERT F, MAHINDA V, et al. Sensor fault detection, isolation and system reconfiguration based on extended Kalman filter for induction motor drives[J]. IET Electric Power Applications, 2013, 7(7): 607-617.
[12]GILBERT H, ZHANG X, VILATHGAMUWA D. A sensor fault detection and isolation method in interior permanent-magnet synchronous motor drives based on an extended Kalman filter[J]. IEEE Transactions on Industry Electronics, 2013, 60(8): 3485-3495.
[13]SHAO S, WASTON J, CLARE J, et al. Robustness analysis and experimental validation of a fault detection and isolation method for the modular multilevel converter[J].IEEE Transactions on Power Electronics, 2016, 31(5): 3794-3805.
[14]XIA J, GUO Y, DAI B, et al. Sensor fault diagnosis and system reconfiguration approach for an electric traction PWM rectifier based on sliding mode observer[J]. IEEE Transactions on Industry Applications, 2017, 53(5): 4768-4778.
[15]BERRIRI H, NAOUAR M, BELKHODJA I. Easy and fast sensor fault detection and isolation algorithm for electrical drives[J].IEEE Transactions on Power Electronics, 2012, 27(2): 490-499.
[16]MENDES A M S,MARQUES CARDOSO A J.Voltage source inverter fault diagnosis in variable speed AC drives,by the average current Park′s vector approach[C]//IEEE International Electric Machines and Drives Conference.IEMDC'99.Proceedings (Cat. No.99EX272).Seattle,WA,USA:IEEE,1999:704-706.
[17]王亚飞.牵引逆变器系统中IGBT与传感器的故障诊断[D].成都:西南交通大学,2016.

基于CGAN与LSTM的逆变器多类型故障诊断方法研究

Multi-Fault Analysis and Diagnosis of Inverters Based on CGAN and LSTM

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价

[1]	易文静, 罗超逵, 罗朝旭, 程谆. 一种低电压应力和电感电流纹波的准Z源逆变器调制策略[J]. 湖南电力, 2023, 43(6): 45-53.
[2]	邱文俊, 李玉齐, 支晓晨, 张顺仁, 陈晓仪, 施宏亮. 光伏电站逆变器与静止无功发生器无功电压控制策略研究与应用[J]. 湖南电力, 2023, 43(6): 138-143.
[3]	邓紫妮, 粟梅, 孙尧, 林建亨. 面向串联补偿三相并网逆变器的模拟阻抗控制策略[J]. 湖南电力, 2023, 43(5): 31-37.
[4]	石曼伶, 罗珍珍, 郑鑫龙, 粟梅. 基于小波相对滑窗能量的直流微电网故障诊断方法[J]. 湖南电力, 2023, 43(5): 49-54.
[5]	易文静, 曹昆, 孟雨薇, 罗朝旭, 程谆. 一种低开关次数和高电压增益的准Z源逆变器不连续调制[J]. 湖南电力, 2023, 43(5): 61-70.
[6]	丁劲松, 姚鸿德, 李圣清, 孟焕平, 朱辉. 民用建筑中光伏逆变器集群谐振机理及分层协调控制[J]. 湖南电力, 2023, 43(4): 32-39.
[7]	王士彬, 李多, 赵娜, 谢文龙, 黄伟, 季鸿宇. 基于改进北方苍鹰算法优化混合核极限学习机的变压器故障诊断方法[J]. 湖南电力, 2023, 43(4): 125-132.
[8]	杨彤, 姜晓峰, 阳瑞霖, 陈威. 基于时域特征参数与振动信号分析的有载分接开关故障诊断[J]. 湖南电力, 2023, 43(3): 125-132.
[9]	曾麟, 朱赞, 徐勇, 向运琨, 何哲. 弱电网下LCL并网逆变器控制设计[J]. 湖南电力, 2023, 43(2): 90-96.
[10]	张阳, 罗超逵, 易文静, 程谆. 基于准Z源模块化多电平换流器的模型预测控制[J]. 湖南电力, 2023, 43(1): 8-16.
[11]	易灵芝, 龙娇, 王雅慧, 黄健雄, 孙涛, 余煌, 禹果. 基于改进天鹰算法优化核极限学习机的油浸式变压器故障诊断研究[J]. 湖南电力, 2022, 42(6): 7-14.
[12]	李振华, 李浩, 黄景光, 张磊, 吴琳. 基于声信号和一维卷积神经网络的绝缘子污秽度监测方法研究[J]. 湖南电力, 2022, 42(4): 18-22.
[13]	李圣清, 沈志超, 彭自然, 何元铭, 谷昕鹏. 基于自适应陷波的光伏逆变器谐振抑制方法[J]. 湖南电力, 2020, 40(6): 5-.