|
|
|
| Operation State Evaluation Method of High-Voltage Shunt Reactor Based on On-Line Monitoring System and Vibro-Acoustic Characteristic Prediction Model |
| Gao Shuguo1, Ji Shengchang2, Meng Lingming1, Tian Yuan1, Zhang Yukun2 |
1. State Grid Hebei Electric Power Research Institute Shijiazhuang 050021 China;
2. State Key Laboratory of Electrical Insulation and Power Equipment Xi’an Jiaotong University Xi’an 710049 China; |
|
|
|
|
Abstract The spectrum characteristics of vibro-acoustic signal are important reference basis for evaluating the operation state of high-voltage shunt reactor. When important structural parts inside the tank become loosing due to long-term vibration, the vibration form of the tank changes, and the change degree of vibro-acoustic characteristics outside the tank also reflects the defect degree of the important structure parts. In this paper, the on-line monitoring system of reactor vibro-acoustic signal is used to continuously monitor vibration signal and acoustic signal of high-voltage shunt reactor tank surface in a substation. Based on historical vibro-acoustic data and time series prediction model, the vibro-acoustic characteristics in the future period are predicted, and the prediction results under long short term memories (LSTM) structure and gated recurrent unit (GRU) structure are compared. The calculation results show that both GRU and LSTM can achieve high accuracy, and GRU saves more time in calculation, which provides timely and effective reference for status evaluation and potential defect diagnosis of high-voltage shunt reactor. On the basis of validating the accuracy of the prediction model, by comparing the overall error between the model output results and the measured results over a period of time, the potential defect and the emergency condition inside the tank can be effectively identified. The research results of this paper can reduce the maintenance cost of substation equipment and improve the intact rate of equipment to a certain extent.
|
|
Received: 08 June 2021
|
|
|
|
|
|
[1] 张鹏宁, 李琳, 程志光, 等. 并联电抗器与变压器模型铁心振动仿真与试验对比[J]. 电工技术学报, 2018, 33(22): 5273-5281.
Zhang Pengning, Li Lin, Cheng Zhiguang, et al.Vibration simulation and experiment comparison of shunt reactor and transformer model core[J]. Transactions of China Electrotechnical Society, 2018, 33(22): 5273-5281.
[2] Zhang Pengning, Li Lin, Cheng Zhiguang, et al.Study on vibration of iron core of transformer and reactor based on maxwell stress and anisotropic magnetostriction[J]. IEEE Transactions on Magnetics, 2019, 55(2): 1-5.
[3] 吴书煜, 马宏忠, 姜宁, 等. 基于多物理场耦合的特高压并联电抗器振动噪声仿真分析与实验研究[J]. 电力自动化设备, 2020, 40(3): 122-127.
Wu Shuyu, Ma Hongzhong, Jiang Ning, et al.Simulation analysis and experimental research on vibration and noise of UHV shunt reactor based on multi physical field coupling[J]. Electric Power Automation Equipment, 2020, 40(3): 122-127.
[4] 张鹏宁, 李琳, 聂京凯, 等. 考虑铁心磁致伸缩与绕组受力的高压并联电抗器振动研究[J]. 电工技术学报, 2018, 33(13): 3130-3139.
Zhang Pengning, Li Lin, Nie Jingkai, et al.Study on the vibration of high voltage shunt reactor considering of magnetostriction and winding force[J]. Transactions of China Electrotechnical Society, 2018, 33(13): 3130-3139.
[5] 吴金利, 马宏忠, 吴书煜, 等.基于振动信号的高压并联电抗器故障诊断方法与监测系统研制[J].电测与仪表, 2020, 57(1): 113-120.
Wu Jinli, Ma Hongzhong, Wu Shuyu, et al.Fault diagnosis method and monitoring system of high voltage parallel reactor based on vibration signal[J]. Electrical Measurement & Instrumentation, 2020, 57(1): 113-120.
[6] 汲胜昌, 张凡, 师愉航, 等. 基于振动信号的电力变压器机械状态诊断方法研究综述[J]. 高电压技术, 2020, 46(1) : 257-272.
Ji Shengchang, Zhang Fan, Shi Yuhang, et al.Review on vibration-based mechanical condition monitoring in power transformers[J]. High Voltage Engineering, 2020, 46(1): 257-272.
[7] 祝令瑜, 沈琪, 汲胜昌, 等. 基于振动测量的电容器装置噪声贡献分析[J]. 电力电容器与无功补偿, 2015, 36(4): 13-17.
Zhu Lingyu, Shen Qi, Ji Shengchang, et a1. Noise contribution analysis of capacitor installations based on measured vibration data[J].Power Capacitor and Reactive Power Compensation, 2015, 36(4):13-17.
[8] Bartoletti C, Desiderio M, Carlo D D, et al.Vibro-acoustic techniques to diagnose power transformers[J]. IEEE Transactions on Power Delivery, 2004, 19(I): 221-229.
[9] Sebastian Borucki.Diagnosis of technical condition of power transformers based on the analysis of vibroacoustic signals measured in transient operating conditions[J]. IEEE Transactions on Power Delivery, 2012, 27(2): 670-676.
[10] 李超然, 肖飞, 樊亚翔, 等. 基于门控循环单元神经网络和Huber-M估计鲁棒卡尔曼滤波融合方法的锂离子电池荷电状态估算方法[J]. 电工技术学报, 2020, 35(9): 207-218.
Li Chaoran, Xiao Fei, Fan Yaxiang, et al.A hybrid approach to lithium-ion battery SOC estimation based on recurrent neural network with gated recurrent unit and Huber-M robust Kalman filter[J]. Transactions of China Electrotechnical Society, 2020, 35(9): 207-218.
[11] 徐奇伟, 黄宏, 张雪锋, 等. 基于改进区域全卷积网络的高压引线接头红外图像特征分析的在线故障诊断方法[J]. 电工技术学报, 2021, 36(7): 1380-1388.
Xu Qiwei, Huang Hong, Zhang Xuefeng, et al.Online fault diagnosis method for infrared image feature analysis of high-voltage lead connectors based on improved R-FCN[J]. Transactions of China Electrotechnical Society, 2021, 36(7): 1380-1388.
[12] 沈小军, 周冲成, 付雪娇. 基于机联网-空间相关性权重的风电机组风速预测研究[J]. 电工技术学报, 2021, 36(9): 1782-1791.
Shen Xiaojun, Zhou Chongcheng, Fu Xuejiao.Wind speed prediction of wind turbine based on the internet of machines and spatial correlation weight[J]. Transactions of China Electrotechnical Society, 2021, 36(9): 1782-1791.
[13] Chen Zaifa, Liu Yancheng, Liu Siyuan, et al.Mechanical state prediction based on LSTM neural netwok[C]//Proceedings of the 36th Chinese Control Conference, Dalian, China, 2017, DOI:10.23919/ ChiCC. 2017.8027963.
[14] Wang Kejun, Qi Xiaoxia, Liu Hongda.Photovoltaic power forecasting based LSTM-convolutional network[J]. Energy, 2019, 189: https://doi.org/10.1016/j.energy.2019.116225.
[15] Song Xuanyi, Liu Yuetian, Xue Liang, et al.Time-series well performance prediction based on long short-term memory (LSTM) neural network model[J/OL]. Journal of Petroleum Science and Engineering, 2020, 208: https://doi.org/10.1016/j.petrol.2021.109686.
[16] 陈畅, 李晓磊, 崔维玉. 基于LSTM网络预测的水轮机机组运行状态检测[J]. 山东大学学报, 2019, 49(3): 39-46.
Chen Chang, Li Xiaolei, Cui Weiyu.Hydraulic turbine operation status detection based on LSTM network prediction[J]. Journal of Shandong University, 2019, 49(3): 39-46.
[17] 杨秋玉, 王栋, 阮江军, 等. 基于振动信号的断路器机械零部件故障程度识别[J]. 电工技术学报, 2021, 36(13): 2880-2892.
Yang Qiuyu, Wang Dong, Ruan Jiangjun, et al.Fault severity estimation method for mechanical parts in circuit breakers based on vibration analysis[J]. Transactions of China Electrotechnical Society, 2021, 36(13): 2880-2892.
[18] Sherstinsky A.Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network[J]. Physica D: Nonlinear Phenomena, 2020, 404: 10.1016/j.physd.2019.132306.
[19] Song Hui, Dai Jiejie, Luo Lingen, et al.Power transformer operating state prediction method based on an LSTM network[J]. Energies, 2018, 11(4): 914.
[20] Bhuvaneswari A, Thomas J, Kesavan P.Embedded bi-directional GRU and LSTM learning models to predict disasterson twitter data[J]. Procedia Computer Science, 2019, 165(165): 511-516.
[21] Athiwaratkun B, Stokes J W.Malware classification with LSTM and GRU language models and a character-level CNN[C]//IEEE International Conference on Acoustics, 2017, DOI:10.1109/ ICASSP. 2017.7952603.
[22] 时珉, 许可, 王珏, 等. 基于灰色关联分析和Geo MAN模型的光伏发电功率短期预测[J]. 电工技术学报, 2021, 36(11): 4050-4059.
Shi Min, Xu Ke, Wang Jue, et al.Short-term photovoltaic power forecast based on grey relational analysis and GeoMAN model[J]. Transactions of China Electrotechnical Society, 2021, 36(11): 4050-4059.
[23] Fu Rui, Zhang Zuo, Li Li.Using LSTM and GRU neural network methods for traffic flow prediction[C]//The 31st Youth Academic Annual Conference of Chinese Association of Automation. Wuhan, China, 2017: 324-328. |
|
|
|
2022, Vol. 37 
