基于VMD-COMTBO-BiLSTM光伏阵列故障诊断研究

史洪岩; 李尚达; 潘多涛; 王国刚

doi:10.19912/j.0254-0096.tynxb.2024-1701

PDF(2102 KB)

太阳能学报 ›› 2026, Vol. 47 ›› Issue (2) : 18-29. DOI: 10.19912/j.0254-0096.tynxb.2024-1701

基于VMD-COMTBO-BiLSTM光伏阵列故障诊断研究

史洪岩^1,2, 李尚达¹, 潘多涛^1,2, 王国刚^1,2

作者信息 +

RESEARCH ON PHOTOVOLTAIC ARRAY FAULT DIAGNOSIS BASED ON VMD-COMTBO-BiLSTM

Shi Hongyan^1,2, Li Shangda¹, Pan Duotao^1,2, Wang Guogang^1,2

Author information +

文章历史 +

摘要

为提高神经网络对光伏阵列故障诊断故障精度,提出一种通过仿真获取数据并进行变分模态分解（VMD）,并通过改进的登山优化算法（COMTBO）,用于双向长短期记忆（BiLSTM）网络的光伏阵列故障诊断。首先,在Matlab/Simulink软件环境下搭建光伏阵列模型,进行数据特征分析,模拟光伏阵列故障,并引入更多的故障特征组成故障数据,使用VMD将故障数据分解成多个分量,并选出最大的能量对应的模态分量作为输入量。然后,提出融合混沌映射、鱼鹰优化算法（OOA）和柯西变异策略的COMTBO算法来实现对BiLSTM的参数寻优,构建VMD-COMTBO-BiLSTM神经网络模型,使光伏阵列故障诊断率达98%,在实际实验中准确率也达99%以上。

Abstract

In order to improve the fault diagnosis accuracy of neural networks for photovoltaic arrays, a method for photovoltaic array fault diagnosis is proposed to obtain data through simulation and perform VMD decomposition, and to use an improved cauchy-osprey-mapping team-based optimization（COMTBO） for bidirectional long short-term memory（BiLSTM） network. Firstly, a photovoltaic array model is built in Matlab/Simulink software environment for data feature analysis, simulating photovoltaic array faults, and introducing more fault features to form fault data. Variational mode decomposition （VMD） is used to decompose the fault data into multiple components, and the modal component corresponding to the maximum energy is selected as the input quantity. Then, a COMTBO algorithm that integrates chaotic mapping, osprey optimization algorithm （OOA）, and cauchy mutation strategy is proposed to optimize the parameters of BiLSTM. A VMD-COMTBO BiLSTM neural network model is constructed to achieve a fault diagnosis rate of 98% for photovoltaic arrays. In actual experiments, the accuracy rate also reaches over 99%.

导出引用

史洪岩, 李尚达, 潘多涛, 王国刚. 基于VMD-COMTBO-BiLSTM光伏阵列故障诊断研究[J]. 太阳能学报. 2026, 47(2): 18-29 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1701

Shi Hongyan, Li Shangda, Pan Duotao, Wang Guogang. RESEARCH ON PHOTOVOLTAIC ARRAY FAULT DIAGNOSIS BASED ON VMD-COMTBO-BiLSTM[J]. Acta Energiae Solaris Sinica. 2026, 47(2): 18-29 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1701

中图分类号： TP615

参考文献

[1] HU Y H, CAO W P, WU J D, et al.Thermography-based virtual MPPT scheme for improving PV energy efficiency under partial shading conditions[J]. IEEE transactions on power electronics, 2014, 29(11): 5667-5672.
[2] 张妍, 裴兴豪, 李冰, 等. 一种基于航拍红外图像的光伏热斑故障分类检测方法[J]. 太阳能学报, 2024, 45(9): 353-359.
ZHANG Y, PEI X H, LI B, et al.Classification detection method of photovoltaic thermal spot in aerial infrared image[J]. Acta energiae solaris sinica, 2024, 45(9): 353-359.
[3] VERGURA S.Criticalities of the outdoor infrared inspection of photovoltaic modules by means of drones[J]. Energies, 2022, 15(14): 5086.
[4] HARROU F, TAGHEZOUIT B, SUN Y.Improved kNN-based monitoring schemes for detecting faults in PV systems[J]. IEEE journal of photovoltaics, 2019, 9(3): 811-821.
[5] DHIMISH M, BADRAN G.Photovoltaic hot-spots fault detection algorithm using fuzzy systems[J]. IEEE transactions on device and materials reliability, 2019, 19(4): 671-679.
[6] 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.
[7] 蔡雨桥, 林培杰, 林耀海, 等. 基于动态时间规整的光伏阵列在线故障检测方法[J]. 电气技术, 2020, 21(7): 42-47.
CAI Y Q, LIN P J, LIN Y H, et al.Online fault detection method for photovoltaic array based on dynamic time warping[J]. Electrical engineering, 2020, 21(7): 42-47.
[8] 马铭遥, 张志祥, 刘恒, 等. 基于I-V特性分析的晶硅光伏组件故障诊断[J]. 太阳能学报, 2021, 42(6): 130-137.
MA M Y, ZHANG Z X, LIU H, et al.Fault diagnosis of crystalline silicon photovoltaic module based on I-V characteristic analysis[J]. Acta energiae solaris sinica, 2021, 42(6): 130-137.
[9] ZHOU S Y, MAO M X, ZHOU L, et al.A shadow fault diagnosis method based on the quantitative analysis of photovoltaic output prediction error[J]. IEEE journal of photovoltaics, 2020, 10(4): 1158-1165.
[10] 张逴, 李树成, 魏东, 等. 基于GS-SVM的光伏阵列积灰程度评估方法研究[J]. 太阳能学报, 2024, 45(11): 220-226.
ZHANG C, LI S C, WEI D, et al.Evaluation method of ash accumulation degree of photovoltaic array based on GS-SVM[J]. Acta energiae solaris sinica, 2024, 45(11): 220-226.
[11] 刘谋海, 邓汉钧, 余敏琪, 等. 基于GOA-SVM模型的光伏阵列故障诊断方法及装置: CN117332325A[P].2024-01-02.
LIU M H, DENG H J, YU M Q, et al. Method and device for photovoltaic array fault diagnosis based on GOA-SVM model: CN117332325A[P].2024-01-02.
[12] WANG M Y, XU X Y, YAN Z.Online fault diagnosis of PV array considering label errors based on distributionally robust logistic regression[J]. Renewable energy, 2023, 203: 68-80.
[13] 王涛, 林培杰, 周海芳, 等. 采用ELM和优化电压传感器布局的光伏阵列故障检测与区域定位[J]. 福州大学学报(自然科学版), 2022, 50(4): 475-482.
WANG T, LIN P J, ZHOU H F, et al.Fault detection and location for photovoltaic array using an optimal voltage sensor placement and extreme learning machine[J]. Journal of Fuzhou University (natural science edition), 2022, 50(4): 475-482.
[14] 谢琳琳, 朱武, 崔昊杨. 改进遗传优化神经网络的光伏阵列故障诊断[J]. 电源技术, 2022, 46(7): 802-806.
XIE L L, ZHU W, CUI H Y.BP netural network based on improved genetic algorithm for fault diagnosis of photovoltaic array[J]. Chinese journal of power sources, 2022, 46(7): 802-806.
[15] LU X Y, LIN Y H, LIN P J, et al.Efficient fault diagnosis approach for solar photovoltaic array using a convolutional neural network in combination of generative adversarial network under small dataset[J]. Solar energy, 2023, 253: 360-374.
[16] 张文军, 林永君, 李静, 等. 基于长短期记忆神经网络的光伏阵列故障诊断[J]. 热力发电, 2021, 50(6): 60-68.
ZHANG W J, LIN Y J, LI J, et al.Fault identification for photovoltaic power generation system based on long short-term memory[J]. Thermal power generation, 2021, 50(6): 60-68.
[17] 张小龙, 汪曦, 于晓光, 等. 基于VMD和LSTM模型的航空液压管路卡箍故障诊断[J]. 液压与气动, 2022, 46(8): 26-33.
ZHANG X L, WANG X, YU X G, et al.Fault diagnosis of aviation hydraulic pipeline clamp based on VMD and LSTM model[J]. Chinese hydraulics & pneumatics, 2022, 46(8): 26-33.
[18] FARIDMEHR I, NEHDI M L, DAVOUDKHANI I F, et al.Mountaineering team-based optimization: a novel human-based metaheuristic algorithm[J]. Mathematics, 2023, 11(5): 1273.
[19] LIN W T, CHANG C M, HUANG Y C, et al.Fault diagnosis in solar array I-V curves using characteristic simulation and multi-input models[J]. Applied sciences, 2024, 14(13): 5417.
[20] XU L C, PAN Z H, LIANG C D, et al.A fault diagnosis method for PV arrays based on new feature extraction and improved the fuzzy C-mean clustering[J]. IEEE journal of photovoltaics, 2022, 12(3): 833-843.
[21] 李斌, 高鹏, 郭自强. 改进蜣螂算法优化LSTM的光伏阵列故障诊断[J]. 电力系统及其自动化学报, 2024, 36(8): 70-78.
LI B, GAO P, GUO Z Q.Improved dung beetle optimizer to optimize LSTM for photovoltaic array fault diagnosis[J]. Proceedings of the CSU-EPSA, 2024, 36(8): 70-78.
[22] HUANG L, FU Q, TONG N.An improved Harris Hawks optimization algorithm and its application in grid map path planning[J]. Biomimetics, 2023, 8(5): 428.
[23] 李爱莲, 全凌翔, 崔桂梅, 等. 融合正余弦和柯西变异的麻雀搜索算法[J]. 计算机工程与应用, 2022, 58(3): 91-99.
LI A L, QUAN L X, CUI G M, et al.Sparrow search algorithm combining sine-cosine and cauchy mutation[J]. Computer engineering and applications, 2022, 58(3): 91-99.
[24] WEN X D, LIU X D, YU C H, et al.IOOA: a multi-strategy fusion improved osprey optimization algorithm for global optimization[J]. Electronic research archive, 2024, 32(3): 2033-2074.