基于数字孪生与融合神经网络的光伏阵列故障诊断

刘卫亮; 姜锴越; 许之胜; 刘帅; 刘长良; 王昕

doi:10.19912/j.0254-0096.tynxb.2023-1124

PDF(2404 KB)

太阳能学报 ›› 2024, Vol. 45 ›› Issue (11) : 303-312. DOI: 10.19912/j.0254-0096.tynxb.2023-1124

基于数字孪生与融合神经网络的光伏阵列故障诊断

刘卫亮^1,2, 姜锴越¹, 许之胜¹, 刘帅^1,2, 刘长良^1,2, 王昕³

作者信息 +

FAULT DIAGNOSIS OF PHOTOVOLTAIC ARRAY BASED ON DIGITAL TWIN AND FUSION NEURAL NETWORK

Liu Weiliang^1,2, Jiang Kaiyue¹, Xu Zhisheng¹, Liu Shuai^1,2, Liu Changliang^1,2, Wang Xin³

Author information +

文章历史 +

摘要

提出一种基于数字孪生模型与融合神经网络的光伏阵列故障诊断方法。首先,设计并初步实现包含孪生模型、数据采集与传输模块、服务应用系统的光伏电站数字孪生系统整体框架;其次,结合机理建模方法与粒子群（PSO）优化算法,建立光伏阵列数字孪生模型;再次,通过评估数字孪生模型输出与物理实体输出之间的残差,对故障进行检测;最后,采用时间卷积网络（TCN）结合双向门控循环单元（BiGRU）的融合神经网络,对光伏阵列故障进行诊断。实验结果表明,所提光伏阵列故障诊断方法较其他方法具有更高的精度,准确率可达97.8%。

Abstract

Photovoltaic power stations are mostly located in harsh environments, so timely and accurate diagnosis of various faults is particularly important. A fault diagnosis method of photovoltaic array based on digital twin model and fusion neural network is proposed. Firstly, the overall framework of digital twin system of PV power station is designed and implemented, which includes twin model, data acquisition and transmission module and service application system. Secondly, combining the mechanism modeling method and particle swarm optimization （PSO） algorithm, the digital twin model of photovoltaic array is established. Thirdly, the fault is detected by evaluating the residual difference between the output of digital twin model and the output of physical entity. Finally, the fault diagnosis of photovoltaic array is carried out by combining temporal convolution network （TCN） with bidirectional gated recurrent unit （BIGRU）. The experimental results show that the proposed fault diagnosis method has higher accuracy than other methods, and the accuracy rate reaches 97.8%.

导出引用

刘卫亮, 姜锴越, 许之胜, 刘帅, 刘长良, 王昕. 基于数字孪生与融合神经网络的光伏阵列故障诊断[J]. 太阳能学报. 2024, 45(11): 303-312 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1124

Liu Weiliang, Jiang Kaiyue, Xu Zhisheng, Liu Shuai, Liu Changliang, Wang Xin. FAULT DIAGNOSIS OF PHOTOVOLTAIC ARRAY BASED ON DIGITAL TWIN AND FUSION NEURAL NETWORK[J]. Acta Energiae Solaris Sinica. 2024, 45(11): 303-312 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1124

中图分类号： TM615

参考文献

[1] 刘志成, 伊晓东, 高飞雪, 等. 绿色碳科学:双碳目标下的科学基础: 第292期“双清论坛” 学术综述[J]. 物理化学学报, 2023, 39(1): 99-107.
LIU Z C, YI X D, GAO F X, et al.Green carbon science: a scientific basis for achieving ‘dual carbon’ goal—academic summary of the 292nd “Shuang-qing forum”[J]. Acta physico-chimica sinica, 2023, 39(1): 99-107.
[2] 刘圣洋, 冬雷, 王晓晓, 等. 基于高斯核模糊C均值聚类的光伏阵列故障诊断方法[J]. 太阳能学报, 2021, 42(5): 286-294.
LIU S Y, DONG L, WANG X X, et al.Photovoltaic array fault diagnosis based on GKFCM[J]. Acta energiae solaris sinica, 2021, 42(5): 286-294.
[3] 李光辉, 段晨东, 武珊. 基于半监督机器学习法的光伏阵列故障诊断[J]. 电网技术, 2020, 44(5): 1908-1913.
LI G H, DUAN C D, WU S.Fault diagnosis of PV array based on semi-supervised machine learning[J]. Power system technology, 2020, 44(5): 1908-1913.
[4] LIU W, HU Y, WANG X, et al.Statistical modeling with hierarchical hidden markov models for fault diagnosis and prognostics of photovoltaic arrays[J]. IEEE transactions on systems, man, and cybernetics: systems, 2019, 49(12): 2597-2610.
[5] ADHYA D, CHATTERJEE S, CHAKRABORTY A K.Stacking ensemble based fault diagnosis approach for improved operation of photovoltaic arrays[J]. Energy sources, part A: recovery, utilization, and environmental effects, 2022, 44(2): 5421-5439.
[6] 贾嵘, 李云桥, 张惠智, 等. 基于改进BP神经网络的光伏阵列多传感器故障检测定位方法[J]. 太阳能学报, 2018, 39(1): 110-116.
JIA R, LI Y Q, ZHANG H Z, et al.Multi-sensor fault detection and positioning method of photovoltaic array based on improved BP neural network[J]. Acta energiae solaris sinica, 2018, 39(1): 110-116.
[7] 陈凌, 韩伟, 张经炜. 基于数据融合的光伏组件故障诊断[J]. 电网技术, 2017, 41(6): 1864-1873.
CHEN L, HAN W, ZHANG J W.PV module fault diagnosis based on data fusion[J]. Power system technology, 2017, 41(6): 1864-1873.
[8] LU X Y, LIN P J,CHENG S Y, et al.Fault diagnosis model for photovoltaic array using a dual-channels convolutional neural network with a feature selection structure[J]. Energy conversion and management, 2021, 248.
[9] 杨帆, 吴涛, 廖瑞金, 等. 数字孪生在电力装备领域中的应用与实现方法[J]. 高电压技术, 2021, 47(5): 1505-1521.
YANG F, WU T, LIAO R J, et al.Application and implementation method of digital twin in electric equipment[J]. High voltage engineering, 2021, 47(5): 1505-1521.
[10] GRIEVES M.Digital twin: manufacturing excellence through virtual factory replication[J]. White paper, 2014, 1(2014): 1-7.
[11] 刘大同, 郭凯, 王本宽, 等. 数字孪生技术综述与展望[J]. 仪器仪表学报, 2018, 39(11): 1-10.
LIU D T, GUO K, WANG B K, et al.Summary and perspective survey on digital twin technology[J]. Chinese journal of scientific instrument, 2018, 39(11): 1-10.
[12] 朱静, 赵静欣. 质子交换膜燃料电池系统数字孪生故障诊断模型研究[J]. 控制理论与应用, 2022, 39(3): 527-534.
ZHU J, ZHAO J X.Digital twin fault diagnosis model analysis of proton exchange membrane fuel cell systems[J]. Control theory & applications, 2022, 39(3): 527-534.
[13] KAIGOM E G, ROSMANN J.Value-driven robotic digital twins in cyber-physical applications[J]. IEEE transactions on industrial informatics, 2021, 17(5): 3609-3619.
[14] WANG H, ZHENG J K, XIANG J W.Online bearing fault diagnosis using numerical simulation models and machine learning classifications[J]. Reliability engineering & system safety, 2023, 234: 109142.
[15] PILTAN F, KIM J M.Crack size identification for bearings using an adaptive digital twin[J]. Sensors, 2021, 21(15): 5009.
[16] YOU L L, ZHU M L.Digital twin simulation for deep learning framework for predicting solar energy market load in trade-by-trade data[J]. Solar energy, 2023, 250: 388-397.
[17] 陶飞, 刘蔚然, 张萌, 等. 数字孪生五维模型及十大领域应用[J]. 计算机集成制造系统, 2019, 25(1): 1-18.
TAO F, LIU W R, ZHANG M, et al.Five-dimension digital twin model and its ten applications[J]. Computer integrated manufacturing systems, 2019, 25(1): 1-18.
[18] ZHANG J W, LIU Y J, LI Y L, et al.A reinforc- ement learning based approach for on-line adaptive parameter extraction of photovoltaic array models[J]. Energy conversion and management, 2020, 214(C): 112875.
[19] WANG J J, YE L K, GAO R X, et al.Digital Twin for rotating machinery fault diagnosis in smart manufacturing[J]. International journal of production research, 2019, 57(12): 3920-3934.
[20] TANG X Z, SHI L F, WANG B, et al.Weight adaptive path tracking control for autonomous vehicles based on PSO-BP neural network[J]. Sensors, 2022, 23(1): 412.
[21] 荀欢欢. 基于数字孪生的舰船上层建筑运维系统[J]. 舰船科学技术, 2023, 45(3): 133-136.
XUN H H.Design of operation and maintenance system for ship superstructure based on digital twin[J]. Ship science and technology, 2023, 45(3): 133-136.
[22] 石辉, 张思远, 刘永刚, 等. 基于数字孪生的电网安全监视与校核技术[J]. 湖南电力, 2021, 41(5): 101-104, 108.
SHI H, ZHANG S Y, LIU Y G, et al.Power grid security monitoring and checking technology based on digital twin[J]. Hunan electric power, 2021, 41(5): 101-104, 108.
[23] BAI S, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[J/OL]. ArXiv Preprint, 2018 ArXiv: 1803.01271.
[24] CHUNG J, GULCEHRE C, CHO K, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[J]. arXiv e-prints, 2014: arXiv: 1412.3555.
[25] MA Y D, WANG Z H, et al.Fault diagnosis by interval-based adaptive thresholds and peak-to-peak observers[J]. International journal of adaptive control and signal processing, 2022, 37(2): 519-537.