基于梅尔倒谱系数特征集的储能变流器开路故障诊断方法

doi:10.11930/j.issn.1004-9649.202205007

中国电力 ›› 2022, Vol. 55 ›› Issue (12): 34-42.DOI: 10.11930/j.issn.1004-9649.202205007

• 新型电力系统储能关键技术应用 • 上一篇下一篇

基于梅尔倒谱系数特征集的储能变流器开路故障诊断方法

余斌¹, 宋兴荣¹, 周挺², 罗林波³, 李辉¹, 车亮⁴

1. 国网湖南省电力有限公司电力科学研究院，湖南长沙 410007;
2. 国网湖南省电力有限公司，湖南长沙 410004;
3. 国网湖南省电力有限公司娄底供电分公司，湖南娄底 417000;
4. 湖南大学电气与信息工程学院，湖南长沙 410082

收稿日期:2022-05-06 修回日期:2022-10-20 发布日期:2022-12-28
作者简介:余斌（1992—），男，硕士，工程师，从事电化学储能电站设计、监控与测试技术研究，E-mail：bindongsanchi@163.com;宋兴荣（1976—），男，硕士，高级工程师，从事电力系统继电保护技术研究，E-mail：songxr@hn.sgcc.com.cn;车亮（1982—），男，通信作者，博士，教授，从事电力系统运行研究，E-mail：cheliang@hnu.com
基金资助:
国家电网有限公司科技项目（5216A521001K）

Open-Circuit Fault Diagnosis Method of Energy Storage Converter Based on MFCC Feature Set

YU Bin¹, SONG Xingrong¹, ZHOU Ting², LUO Linbo³, LI Hui¹, CHE Liang⁴

1. Electric Power Research Institute of State Grid Hunan Electric Power Company Limited, Changsha 410007, China;
2. State Grid Hunan Electric Power Company Limited, Changsha 410004, China;
3. State Grid Loudi Power Supply Company, Loudi 417000, China;
4. College of Electrical and Information Engineering, Hunan University, Changsha 410082, China

Received:2022-05-06 Revised:2022-10-20 Published:2022-12-28
Supported by:
This work is supported by Science and Technology Project of SGCC (No.5216A521001K).

摘要/Abstract

摘要： 电池储能电站功率转换系统（power conversion system，PCS）故障诊断在储能电站智能运维中发挥着重要作用。现有方法在非侵入式识别PCS内部IGBT开路故障时，易出现信号特征提取困难、数据维度爆炸以及阈值判定区间不稳定等问题。提出一种基于梅尔倒谱系数（Mel-scale frequency cepstral coefficients，MFCC）特征集的储能变流器开路故障诊断方法。首先，以交流侧三相电流为输入信号，通过分析不同频率区间的信号频谱能量分布情况和包络特征，构建MFCC故障特征数据集。然后，结合核主成分分析（kernel principal components analysis，KPCA），实现充放电工况下非线性故障特征的降维筛选；其次，以低维故障特征集为输入，构建基于贝叶斯优化算法（bayesian optimization algorithm，BOA）与一维卷积神经网络（1d-convolutional neural network，CNN-1D）的故障状态诊断模型；最后，通过并网储能变流器的故障仿真实验，与现有方法进行比较，结果表明：所提方法在复杂的噪声环境下的鲁棒性和准确性更优。

关键词: 电池储能, 变流器, 故障诊断, 梅尔倒谱系数, 诊断模型

Abstract: Power conversion system (PCS) fault diagnosis plays an important role in the intelligent operation and maintenance of battery energy storage power stations. Considering the difficulties in signal feature extraction, data dimension explosion, and instability of threshold determination interval in the non-invasive identification of IGBT open-circuit fault in PCS by the existing methods, this paper proposes an open-circuit fault diagnosis method of energy storage converter based on Mel-scale frequency cepstral coefficients (MFCC) feature set, so as to support the normal operation and maintenance of PCS. Firstly, the three-phase current on the alternating current (AC) side is taken as the input signal, and an MFCC fault feature data set is constructed by analyzing the signal spectrum energy distribution and envelope characteristics in different frequency intervals. Then, through kernel principal component analysis (KPCA), the dimension reduction screening of nonlinear fault features under charge and discharge conditions is realized. Secondly, a fault state diagnosis model based on the Bayesian optimization algorithm (BOA) and one-dimensional convolutional neural network (CNN-1D) is constructed with a low-dimensional fault feature set as an input. Finally, through the fault simulation experiment of a grid-connected energy storage converter, the proposed method is compared with existing methods, and the results show that the proposed method has better robustness and accuracy in complex noise environments.

Key words: battery energy storage, converter, fault diagnosis, Mel-scale frequency cepstral coefficients, diagnosis model

余斌, 宋兴荣, 周挺, 罗林波, 李辉, 车亮. 基于梅尔倒谱系数特征集的储能变流器开路故障诊断方法[J]. 中国电力, 2022, 55(12): 34-42.

YU Bin, SONG Xingrong, ZHOU Ting, LUO Linbo, LI Hui, CHE Liang. Open-Circuit Fault Diagnosis Method of Energy Storage Converter Based on MFCC Feature Set[J]. Electric Power, 2022, 55(12): 34-42.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202205007

https://www.electricpower.com.cn/CN/Y2022/V55/I12/34

参考文献

[1] 李彦林, 王明彦, 郑载满. 微网运行条件下储能并网VSC多目标控制策略[J]. 电网技术, 2013, 37(7): 1792–1798
LI Yanlin, WANG Mingyan, ZHENG Zaiman. A multi-objective control strategy for grid-connecting VSC under grid-connected operation of microgrid[J]. Power System Technology, 2013, 37(7): 1792–1798
[2] 元博, 张运洲, 鲁刚, 等. 电力系统中储能发展前景及应用关键问题研究[J]. 中国电力, 2019, 52(3): 1–8
YUAN Bo, ZHANG Yunzhou, LU Gang, et al. Research on key issues of energy storage development and application in power systems[J]. Electric Power, 2019, 52(3): 1–8
[3] 宋平岗, 吴继珍, 邹欢. 电网电压不平衡时模块化多电平换流器直接功率补偿控制策略[J]. 高电压技术, 2016, 42(7): 2184–2192
SONG Pinggang, WU Jizhen, ZOU Huan. Direct power compensation control strategy for modular multilevel converter under unbalanced grid voltage conditions[J]. High Voltage Engineering, 2016, 42(7): 2184–2192
[4] 欧名勇, 王逸超, 刘文军, 等. 电网电压不平衡下储能变流器的控制策略[J]. 中国电力, 2022, 55(7): 93–101
OU Mingyong, WANG Yichao, LIU Wenjun, et al. Control strategy of power conversion system under unbalanced grid voltage[J]. Electric Power, 2022, 55(7): 93–101
[5] 余斌, 朱维钧, 徐浩, 等. 电池储能电站电池管理系统关键技术[J]. 湖南电力, 2020, 40(5): 55–59
YU Bin, ZHU Weijun, XU Hao, et al. Key technology of battery management system in battery storage power station[J]. Hunan Electric Power, 2020, 40(5): 55–59
[6] 张筱辰, 朱金大, 杨冬梅, 等. 基于t-SNE流形学习与快速聚类算法的光伏逆变器故障预测技术[J]. 中国电力, 2020, 53(6): 41–47
ZHANG Xiaochen, ZHU Jinda, YANG Dongmei, et al. Photovoltaic inverter fault prediction technology based on t-SNE manifold learning and fast clustering algorithm[J]. Electric Power, 2020, 53(6): 41–47
[7] 马铭遥, 凌峰, 孙雅蓉, 等. 三相电压型逆变器智能化故障诊断方法综述[J]. 中国电机工程学报, 2020, 40(23): 7683–7699
MA Mingyao, LING Feng, SUN Yarong, et al. Review of intelligent fault diagnosis methods for three-phase voltage-mode inverters[J]. Proceedings of the CSEE, 2020, 40(23): 7683–7699
[8] ZHANG J H, ZHAO J, ZHOU D H, et al. High-performance fault diagnosis in PWM voltage-source inverters for vector-controlled induction motor drives[J]. IEEE Transactions on Power Electronics, 2014, 29(11): 6087–6099.
[9] LI M S, YU D, CHEN Z M, et al. A data-driven residual-based method for fault diagnosis and isolation in wind turbines[J]. IEEE Transactions on Sustainable Energy, 2019, 10(2): 895–904.
[10] CAI B P, ZHAO Y B, LIU H L, et al. A data-driven fault diagnosis methodology in three-phase inverters for PMSM drive systems[J]. IEEE Transactions on Power Electronics, 2017, 32(7): 5590–5600.
[11] NTALAMPIRAS S. Fault diagnosis for smart grids in pragmatic conditions[J]. IEEE Transactions on Smart Grid, 2018, 9(3): 1964–1971.
[12] 杨彦杰, 董哲, 姚芳, 等. 基于1 D-CNN-LSTM混合神经网络模型的双桥并联励磁功率单元故障诊断[J]. 电网技术, 2021, 45(5): 2025–2032
YANG Yanjie, DONG Zhe, YAO Fang, et al. Fault diagnosis of double bridge parallel excitation power unit based on 1 D-CNN-LSTM hybrid neural network model[J]. Power System Technology, 2021, 45(5): 2025–2032
[13] WANG T Z, QI J, XU H, et al. Fault diagnosis method based on FFT-RPCA-SVM for Cascaded-Multilevel Inverter[J]. ISA Transactions, 2016, 60: 156–163.
[14] 姜媛媛, 王友仁, 吴祎, 等. 基于小波包能量谱和ELM的光伏逆变器多故障在线诊断[J]. 仪器仪表学报, 2015, 36(9): 2145–2152
JIANG Yuanyuan, WANG Youren, WU Yi, et al. Online multiple fault diagnosis for PV inverter based on wavelet packet energy spectrum and extreme learning machine[J]. Chinese Journal of Scientific Instrument, 2015, 36(9): 2145–2152
[15] 陈勇, 刘志龙, 陈章勇. 基于电流矢量特征分析的逆变器开路故障快速诊断与定位方法[J]. 电工技术学报, 2018, 33(4): 883–891
CHEN Yong, LIU Zhilong, CHEN Zhangyong. Fast diagnosis and location method for open-circuit fault in inverter based on current vector character analysis[J]. Transactions of China Electrotechnical Society, 2018, 33(4): 883–891
[16] GOMATHY V, SELVAPERUMAL S. Fault detection and classification with optimization techniques for a three-phase single-inverter circuit[J]. Journal of Power Electronics, 2016, 16: 1097–1109.
[17] 张建忠, 耿治, 徐帅. 基于T型逆变器的APF故障诊断与容错控制[J]. 中国电机工程学报, 2019, 39(1): 245–255, 339
ZHANG Jianzhong, GENG Zhi, XU Shuai. Fault diagnosis and fault tolerant control for APF based on T-type inverter[J]. Proceedings of the CSEE, 2019, 39(1): 245–255, 339
[18] 严亚兵, 朱维钧, 欧阳帆, 等. 基于频域分析的储能变流器控制相互作用研究[J]. 湖南电力, 2019, 39(5): 13–17
YAN Yabing, ZHU Weijun, OUYANG Fan, et al. Research on control interaction of energy storage converter based on frequency domain analysis[J]. Hunan Electric Power, 2019, 39(5): 13–17
[19] MA J C, SHANG J N, ZHAO X, et al. Bayes-DCGRU with Bayesian optimization for rolling bearing fault diagnosis[J]. Applied Intelligence, 2022, 52(10): 11172–11183.
[20] 曹浩, 黄韬, 周舟, 等. 基于主成分分析法的变压器直流偏磁声学异常检测[J]. 湖南电力, 2021, 41(5): 1–6
CAO Hao, HUANG Tao, ZHOU Zhou, et al. Detection of DC bias magnetic acoustic abnormality of transformer based on principal component analysis[J]. Hunan Electric Power, 2021, 41(5): 1–6

基于梅尔倒谱系数特征集的储能变流器开路故障诊断方法

Open-Circuit Fault Diagnosis Method of Energy Storage Converter Based on MFCC Feature Set

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	刘雨姗, 陈俊儒, 常喜强, 刘牧阳. 构网型储能变流器并网性能的多层级评价指标体系及应用[J]. 中国电力, 2025, 58(3): 193-203.
[2]	许常昊, 关伟东, 王越, 张金帅, 王鹏, 周宁, 尚博文. 全功率小型变速抽水蓄能机组双层MPC虚拟惯量控制策略[J]. 中国电力, 2025, 58(2): 216-226.
[3]	彭昊, 罗正经, 夏向阳, 曾刚, 欧宇健, 陈贵全, 王继军, 刘立洪. 储能系统多电池簇健康状态均衡控制策略[J]. 中国电力, 2024, 57(6): 45-52.
[4]	夏向阳, 蒋戴宇, 曾小勇, 龚芬, 吴小忠, 华夏, 罗彦鹏, 石超. 基于虚拟振荡器控制的储能变流器控制策略研究[J]. 中国电力, 2024, 57(11): 70-77.
[5]	李世龙, 李龙江, 刘欣博, 张华. 一种增强稳定性的储能变流器线性自抗扰控制参数整定方法[J]. 中国电力, 2024, 57(10): 25-35.
[6]	刘贺千, 张健, 张海月, 杨洪达, 陈世玉, 申昱博, 王磊. 基于高频阻抗谱的干式空心电抗器匝间短路故障诊断方法[J]. 中国电力, 2024, 57(10): 218-224.
[7]	徐佳, 杨树德, 张新闻. 基于并网电流谐波反馈的有源阻尼策略[J]. 中国电力, 2023, 56(8): 126-135.
[8]	卢子敬, 李子寿, 郭相国, 杨博. 基于多目标人工蜂鸟算法的电-氢混合储能系统最优配置[J]. 中国电力, 2023, 56(7): 33-42.
[9]	黎燕, 程馨, 黄祖梁, 杨琢. 高可靠性三相多功能并网变换器研究[J]. 中国电力, 2023, 56(5): 172-181.
[10]	李刚, 孟坤, 贺帅, 刘云鹏, 杨宁. 考虑特征耦合的Bi-LSTM变压器故障诊断方法[J]. 中国电力, 2023, 56(3): 100-108,117.
[11]	刘振国, 金铭, 于海, 陈文涛, 杨定乾. 交流微电网直流互联变流器系统多阻抗优化控制[J]. 中国电力, 2023, 56(2): 93-101,156.
[12]	韩伟, 段文岩, 杜兴伟, 姚峰, 马伟东, 刘磊. 基于数字孪生的在运安控系统故障诊断方法[J]. 中国电力, 2023, 56(11): 121-127.
[13]	马海飞, 滕伟, 彭迪康, 柳亦兵, 靳涛. 基于DRS与改进Autogram的风电齿轮箱复合故障特征提取[J]. 中国电力, 2023, 56(10): 71-79.
[14]	王爽, 罗倩, 唐波, 姜岚, 李锦. 考虑样本类内不平衡的CHPOA-DBN变压器故障诊断方法[J]. 中国电力, 2023, 56(10): 133-144.
[15]	张宏杰, 陈贵凤, 闫宏伟, 杨晓龙, 侯天仁, 张伟. 基于SMOTE与Bayes优化的LSTM网络变压器故障诊断[J]. 中国电力, 2023, 56(10): 164-170.

模态框（Modal）标题

基于梅尔倒谱系数特征集的储能变流器开路故障诊断方法

Open-Circuit Fault Diagnosis Method of Energy Storage Converter Based on MFCC Feature Set

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics