Classification and Recognition Method of Transformer Operating State Based on ECA-CNN-BiLSTM Optimized by HPO
CSTR:
Author:
Affiliation:

1.School of Electrical Engineering, Chongqing University;2.China Southern Power Grid Yunnan Power Grid Co., Ltd. Electric Power Research Institute;3.School of Automation, Nanjing University of Science and Technology

Fund Project:

The National Natural Science Foundation of China

  • Article
  • | |
  • Metrics
  • |
  • Reference [54]
  • | |
  • Cited by
  • | |
  • Comments
    Abstract:

    The classification and accurate recognition of transformer operating states are very important for the stable operation of transformers and the safe power supply of power systems. At present, there are still some problems in this kind of research, such as less attention to the relevant data of transformer loads, high complexity of mechanism models and unclear correlation between oil temperature data and overload state. Therefore, this paper proposes an improved hybrid model that combines the hunter-prey optimization (HPO) algorithm with the efficient channel attention (ECA) module, applied to convolutional neural networks (CNN) and bidirectional long short-term memory (BiLSTM) neural networks. It is used to classify transformer operating state and identify overload fault. The data of a main transformer containing nine characteristics related to transformer load are selected as samples, and the load state category is selected through K-Means ++ clustering and transformer normal periodic load analysis. The parameters of the hybrid model were optimized by HPO to improve the performance and generalization ability. Through pre-processing and feature extraction of transformer load data, the improved model is used to recognize the load state accurately. The experimental results show that the recognition accuracy of this method can reach 99.24%, and good results are obtained in the task of transformer operating state classification.

    Reference
    [1] 李刚, 于长海, 刘云鹏, 等. 电力变压器故障预测与健康管理: 挑战与展望[J]. 电力系统自动化, 2017, 41(23): 156-167.
    LI Gang, YU Changhai, LIU Yunpeng, et al. Fault prediction and health management of power transformers: Challenges and Prospects [J]. Automation of Electric Power Systems, 2017, 41(23): 156-167.
    [3] [2] 周光宇, 马松龄. 基于机器学习与DGA的变压器故障诊断及定位研究[J]. 高压电器, 2020, 56(06): 262-268.
    ZHOU Guangyu, MA Songling. Research on Transformer fault Diagnosis and Location based on Machine Learning and DGA [J]. High Voltage Electrical Apparatus, 2020, 56(06): 262-268.
    [5] [3] 张邵杰. 基于烟花算法优化SVM的变压器故障诊断[J]. 机电信息, 2021(22): 30–31.
    ZHANG Shaojie. Transformer Fault Diagnosis based on Fireworks Algorithm optimization SVM [J]. Mechanical and Electrical Information, 2021(22): 30-31.
    [7] [4] 向小民, 盛刘宇, 刘谦等. 基于特征选择和ICOA-LSSVM的变压器故障诊断[J/OL]. 电气工程学报:1-9[2024-03-25].http://kns.cnki.net/kcms/detail/10.1289.TM.20231027.1033.002.html.
    XIANG Xiaomin, SHENG Liuyu, LIU Qian, et al. Transformer fault diagnosis based on feature selection and ICOA-LSSVM [J/OL]. Journal of Electrical Engineering: 1-9[2024-03-25].http://kns.cnki.net/kcms/detail/10.1289.TM.20231027.1033.002.html.
    [9] [5] 宋立业, 范抑伶, 王燚增. 基于KPCA与IHHO-LSSVM的电力变压器故障诊断方法研究[J]. 电气工程学报, 2022, 17(01): 95-103.
    SONG Liye, FAN Yiling, WANG Yizeng. Research on Power Transformer Fault diagnosis Method Based on KPCA and IHHO-LSSVM [J]. Journal of Electrical Engineering, 2022, 17(01): 95-103.
    [11] [6] 夏洪刚, 郭红兵, 肖金超. 基于CNN的电力变压器故障诊断方法[J]. 电子设计工程, 2020, 28(13): 189–193.
    XIA Honggang, GUO Hongbing, XIAO Jinchao. Fault diagnosis method of power transformer based on CNN [J]. Electronic Design Engineering, 2020, 28(13): 189-193.
    [13] [7] TAHA I B M, IBRAHIM S, MANSOUR D E A. Power transformer fault diagnosis based on DGA using a convolutional neural network with noise in measurements[J]. IEEE Access, 2021, 9: 111162?111170.
    [14] [8] 崔宇, 侯慧娟, 胥明凯, 等. 基于双重注意力机制的变压器油中溶解气体预测模型[J]. 中国电机工程学报, 2020, 40(1): 338–347, 400.
    CUI Yu, HOU Huijuan, XU Mingkai, et al. Prediction Model of Dissolved Gas in Transformer Oil based on Double Attention Mechanism [J]. Proceedings of the CSEE, 2020, 40(1): 338-347, 400.
    [16] [9] CHEN P, TOYOTA T, HE Z. Automated function generation of symptom parameters and application to fault diagnosis of machinery under variable operating conditions[J]. IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans. 2001(6): 775-781.
    [17] [10] 吴晓欣, 何怡刚, 段嘉珺, 等. 考虑复杂时序关联特性的Bi-LSTM变压器DGA故障诊断方法[J]. 电力自动化设备, 2020, 40(08): 184-193.
    WU Xiaoxin, HE Yigang, DUAN Jiajun, et al. DGA Fault Diagnosis Method of Bi?LSTM Transformer Considering Complex Temporal Correlation [J]. Electric Power Automation Equipment, 2020, 40(8): 184?190.
    [19] [11] 范晓丹, 付炜平, 赵智龙, 等. 基于长短时记忆网络油浸式变压器故障诊断研究[J]. 变压器, 2021, 58(9): 27?32.
    FAN Xiaodan, FU Weiping, ZHAO Zhilong, et al. Fault diagnosis of Oil-immersed Transformer Based on Long/short Time Memory Network [J]. Transformers, 2021, 58(9): 27?32.
    [21] [12] 赵珣, 陈帅, 邱海洋. 基于改进双向循环神经网络的变压器故障诊断模型研究[J]. 辽宁石油化工大学学报, 2023, 43(05): 75-83.
    ZHAO Xun, CHEN Shuai, QIU Haiyang. Research on Transformer Fault Diagnosis Model Based on Improved Bidirectional Recurrent Neural Network [J]. Journal of Liaoning Shihua University, 2023, 43(05): 75-83.
    [23] [13] 廖才波, 杨金鑫, 邱志斌, 等. 基于缺失数据填补的油浸式变压器故障诊断[J/OL]. 高电压技术:1-10 [2024-03-12].https://doi.org/10.13336/j.1003-6520.hve.20231532.
    LIAO Caibo, YANG Jinxin, QIU Zhibin, et al. Fault diagnosis of Oil-immersed transformer based on Missing data filling [J/OL]. High Voltage Technology :1-10 [2024-03-12].https://doi.org/10.13336/j.1003-6520.hve.20231532.
    [25] [14] 刘超, 刘洋, 韩刚, 等. 改进Dempster-Shafer证据与概率模型集成的变压器故障诊断[J/OL]. 电力系统及其自动化学报:1-12[2024-03-12].https://doi.org/10.19635/j. cnki.csu-epsa.001395.
    LIU Chao, LIU Yang, HAN Gang, et al. Transformer fault diagnosis with improved integration of Dempster-Shafer evidence and probabilistic model [J/OL]. Journal of Electric Power Systems and Automation :1-12[2024-03- 12].https://doi.org/10.19635/j.cnki.csu-epsa.001395.
    [27] [15] Huo-Ching Sun, Yan-Chang Huang, Chao-Ming Huang. Fault Diagnosi of Power Transformers Using Computational Intelligence: A Review[J]. Energy Procedia, 2012, 14: 1226-1231.
    [28] [16] 严莉, 王维建, 周东华. 变压器故障诊断的油色谱分析方法综述[J]. 控制工程, 2003(06): 488-491.
    YAN Li, WANG Weijian, ZHOU Donghua. Review of oil chromatography analysis methods for Transformer fault diagnosis [J]. Control Engineering, 2003(06): 488-491.
    [30] [17] 刘刚, 兰和潼, 姜雄伟, 等. 基于温升特性的强迫导向油循环风冷结构变压器负荷能力评估[J/OL]. 高电压技术, 2024: 1-11. 刘刚, 兰和潼, 姜雄伟, 等. 基于温升特性的强迫导向油循环风冷结构变压器负荷能力评估[J/OL]. 高电压技术, 2024: 1-11. [2024-01-15]. https://doi.org/10.13336/j.1003-6520.hve.20230314.
    LIU Gang, LAN Hetong, JIANG Xiongwei, et al. Load capacity evaluation of forced-guided oil circulation air-cooled transformer based on temperature rise characteristics [J/OL]. High Voltage Technology, 2024: 1-11.[2024-01-15].https://doi.org/10.13336/j.1003-6520.hve.20230314.
    [32] [18] 周利军, 唐浩龙, 王路伽, 等. 基于顶层油温升的变压器过负载建模与分析[J]. 高电压技术, 2019, 45(08): 2502-2508.
    ZHOU Lijun, TANG Haolong, Wang Lujia, et al. Modeling and Analysis of Transformer Overload based on Top Oil Temperature Rise [J]. High Voltage Technology, 2019, 45(08): 2502-2508.
    [34] [19] 钱瞳. 油浸式电力变压器热模型研究及负载能力评估[D]. 华南理工大学, 2018.
    QIAN Tong. Thermal Model research and load capacity Evaluation of oil-immersed power transformer [D]. South China University of Technology, 2018.
    [36] [20] 夏伊乔, 郭创新, 陈玉峰, 等. 考虑多因素的变压器过负荷性能评价模型[J]. 机电工程, 2017, 34(05): 509-514.XIA Yiqiao, GUO Xincheng, CHEN Yufeng, et al. Evaluation model of transformer overload performance considering multiple factors [J]. Mechanical and Electrical Engineering, 2017, 34(05): 509-514.
    [37] [21] 张翔, 宋子彤, 杨致慧, 等. 一种基于负载率和设备检测信息的油浸式变压器故障率模型[J]. 电网技术, 2013, 37(04): 1159-1165.
    ZHANG Xiang, SONG Zitong, YANG Zhihui, et al. A failure rate model of oil-immersed transformer based on load rate and equipment detection information [J]. Power Grid Technology, 2013, 37(04): 1159-1165.
    [39] [22] 朱柳慧. 变压器过载能力优化及运行风险评估方法[D]. 上海交通大学, 2013.
    ZHU Liuhui. Optimization of transformer overload capacity and Operation Risk Assessment Method [D]. Shanghai Jiao Tong University, 2013.
    [41] [23] 唐文虎, 钱瞳, 黄晶晶, 等. 用于变压器负载能力评估的改进热电类比模型[J]. 华南理工大学学报(自然科学版), 2017, 45(10): 71-77, 86.
    TANG Wenhu, QIAN Tong, HUANG Jingjing, et al. Improved thermoelectric analog model for Transformer Load capacity Evaluation [J]. Journal of South China University of Technology (Natural Science Edition), 2017, 45(10): 71-77, 86.
    [43] [24] Shiravand V, Faiz J, Samimi M H, et al. Improving the transformer thermal modeling by considering additional thermal points[J]. International Journal of Electrical Power & Energy Systems, 2021, 128(11): 106748.
    [44] [25] Aslam M, Haq I U, Rehan M S, et al. Dynamic thermal model for power transformers[J]. IEEE ACCESS, 2021, 9: 71461-71469.
    [45] [26] 张晓华, 吕志瑞, 孙云生, 等. 基于修正热路模型的油浸式变压器绕组热点温度计算研究[J/OL]. 电测与仪表:1-9[2024-03-13].http://kns.cnki.net/kcms/detail/23.1202.TH.20220622.1157.006.html.
    ZHANG Xiaohua, LU Zhirui, SUN Yunsheng, et al. Research on Hot Spot Temperature calculation of oil-immersed transformer winding based on modified hot path model [J/OL]. Electrical measurement and instrumentation :1-9[2024-03-13].http://kns.cnki.net/kcms/detail/23.1202.TH.20220622.1157.006.html.
    [47] [27] 章浩. 计及辅助散热的ONAN变压器改进热路模型及负载能力评估[D]. 华南理工大学, 2022.
    ZHANG Hao. Improved thermal path model and load capacity evaluation of ONAN Transformer with auxiliary heat dissipation [D]. South China University of Technology, 2022.
    [49] [28] 袁发庭, 杨文韬, 韩毅凛, 等. 基于电磁-流热双向耦合的变压器绕组温升计算及结构参数优化研究[J/OL]. 高电压技术:1-11[2024-03-13].https://doi.org/10.13336/ j.1003-6520.hve.20221530.
    YUAN Fating, YANG Wentao, HAN Yilin, et al. Research on Temperature Rise Calculation and Structural Parameter Optimization of Transformer winding based on Electromagnetic and fluid-heat coupling [J/OL]. High voltage technology :1-11[2024-03-13].https://doi.org/10. 13336/j.1003-6520.hve.20221530.
    [51] [29] 刘佳翰, 陈克绪, 马建, 等. 基于卷积神经网络和随机森林的三相电压暂降分类[J]. 电力系统保护与控制, 2019, 47(20): 112-118.
    LIU Jiahan, CHEN Kexu, MA Jian, et al. Three-phase voltage dip classification based on Convolutional neural network and Random forest [J]. Power System Protection and Control, 2019, 47(20): 112-118.
    [53] [30] Qilong Wang, Banggu Wu, Peng Fei Zhu, et al. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks[C]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019: 11531-11539.
    [54] [31] Naruei I, Keynia F, Sabbagh Molahosseini A. Hunter–prey optimization: algorithm and applications[J]. Soft Computing, 2022, 26: 1279-1314.
    Related
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation
Share
Article Metrics
  • Abstract:26
  • PDF: 0
  • HTML: 0
  • Cited by: 0
History
  • Received:June 05,2024
  • Revised:July 04,2024
  • Adopted:July 10,2024
Article QR Code

Address:No. 219, Ningliu Road, Nanjing, Jiangsu Province

Postcode:210044

Phone:025-58731025