基于梯度提升回归树-自训练贝叶斯优化支持向量机的光伏阵列故障诊断方法

曹岚; 周成功; 袁斌霞; 沈银钢

doi:10.19912/j.0254-0096.tynxb.2024-0278

PDF(2809 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (6) : 289-297. DOI: 10.19912/j.0254-0096.tynxb.2024-0278

基于梯度提升回归树-自训练贝叶斯优化支持向量机的光伏阵列故障诊断方法

曹岚, 周成功, 袁斌霞, 沈银钢

作者信息 +

FAULT DIAGNOSIS METHODS OF PHOTOVOLTAIC ARRAYS BASED ON GRADIENT BOOSTING REGRESSION TREE-SELF-TRAINING BAYESIAN OPTIMIZED SUPPORT VECTOR MACHINE

Cao Lan, Zhou Chenggong, Yuan Binxia, Shen Yin'gang

Author information +

文章历史 +

摘要

提出一种基于梯度提升回归树-自训练贝叶斯优化支持向量机的光伏阵列故障诊断方法。实验结果表明,在无法直接测得开路电压的情况下,梯度提升回归树-自训练贝叶斯优化支持向量机算法预测开路电压并将其作为特征参数进行故障诊断的准确率为94.96%,运行时间为4.876 s,具有较好的准确率和较短的诊断时间。

Abstract

A fault diagnosis method for PV arrays, based on the gradient-boosted regression tree-self-training Bayesian optimized support vector machine, is proposed aiming at the difficulty of measuring open-circuit voltage directly by conventional monitoring systems. The experimental results show that in the case where the open-circuit voltage cannot be directly measured, the accuracy rate of the gradient-boosted regression tree-self-trained Bayesian optimized support vector machine algorithm in predicting open-circuit voltage and using it as a characteristic parameter for fault diagnosis is 94.96%, and a running time of 4.876 s, which has better accuracy and a shorter diagnosis time.

导出引用

曹岚, 周成功, 袁斌霞, 沈银钢. 基于梯度提升回归树-自训练贝叶斯优化支持向量机的光伏阵列故障诊断方法[J]. 太阳能学报. 2025, 46(6): 289-297 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0278

Cao Lan, Zhou Chenggong, Yuan Binxia, Shen Yin'gang. FAULT DIAGNOSIS METHODS OF PHOTOVOLTAIC ARRAYS BASED ON GRADIENT BOOSTING REGRESSION TREE-SELF-TRAINING BAYESIAN OPTIMIZED SUPPORT VECTOR MACHINE[J]. Acta Energiae Solaris Sinica. 2025, 46(6): 289-297 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0278

中图分类号： TK514

参考文献

[1] PEINADO GONZALO A, PLIEGO MARUGÁN A, GARCÍA MÁRQUEZ F P. Survey of maintenance management for photovoltaic power systems[J]. Renewable and sustainable energy reviews, 2020, 134: 110347.
[2] LI B, DELPHA C, DIALLO D, et al.Application of artificial neural networks to photovoltaic fault detection and diagnosis: a review[J]. Renewable and sustainable energy reviews, 2021, 138: 110512.
[3] VAN GOMPEL J, SPINA D, DEVELDER C.Satellite based fault diagnosis of photovoltaic systems using recurrent neural networks[J]. Applied energy, 2022, 305: 117874.
[4] LODHI E, WANG F Y, XIONG G, et al.An AdaBoost ensemble model for fault detection and classification in photovoltaic arrays[J]. IEEE journal of radio frequency identification, 2022, 6: 794-800.
[5] 唐圣学, 王彦丰, 乔乃珍. 光伏发电系统直流串联故障电弧检测方法研究[J]. 太阳能学报, 2023, 44(11): 31-39.
TANG S X, WANG Y F, QIAO N Z.Study on detection method of DC fault arc based on photovoltaic power generation system[J]. Acta energiae solaris sinica, 2023, 44(11): 31-39.
[6] NAVEEN VENKATESH S, SUGUMARAN V.Machine vision based fault diagnosis of photovoltaic modules using lazy learning approach[J]. Measurement, 2022, 191: 110786.
[7] MELLIT A.An embedded solution for fault detection and diagnosis of photovoltaic modules using thermographic images and deep convolutional neural networks[J]. Engineering applications of artificial intelligence, 2022, 116: 105459.
[8] KORKMAZ D, ACIKGOZ H.An efficient fault classification method in solar photovoltaic modules using transfer learning and multi-scale convolutional neural network[J]. Engineering applications of artificial intelligence, 2022, 113: 104959.
[9] 任惠, 夏静, 卢锦玲, 等. 基于红外图像和改进MobileNet-V3的光伏组件故障诊断方法[J]. 太阳能学报, 2023, 44(8): 238-245.
REN H, XIA J, LU J L, et al.Research on fault diagnosis of photovoltaic modules based on infrared images and improved MobileNet-V3[J]. Acta energiae solaris sinica, 2023, 44(8): 238-245.
[10] 陈辉, 张傲, 孙帅, 等. 基于改进DeepLabv³+的含噪声热红外图像光伏热斑检测方法[J]. 太阳能学报, 2023, 44(11): 23-30.
CHEN H, ZHANG A, SUN S, et al.Photovoltaic thermal spot detection method with noisy thermal infrared image based on improved DeepLabv³+[J]. Acta energiae solaris sinica, 2023, 44(11): 23-30.
[11] HUANG J M, WAI R J, GAO W.Newly-designed fault diagnostic method for solar photovoltaic generation system based on IV-curve measurement[J]. IEEE access, 2019, 7: 70919-70932.
[12] 陶彩霞, 王旭, 高锋阳. 基于深度信念网络的光伏阵列故障诊断[J]. 中国电力, 2019, 52(12): 105-112.
TAO C X, WANG X, GAO F Y.Fault diagnosis of photovoltaic array based on deep belief network[J]. Electric power, 2019, 52(12): 105-112.
[13] CHEN Z C, WU L J, CHENG S Y, et al.Intelligent fault diagnosis of photovoltaic arrays based on optimized kernel extreme learning machine and I-V characteristics[J]. Applied energy, 2017, 204: 912-931.
[14] ZHAO Q, SHAO S, LU L X, et al.A new PV array fault diagnosis method using fuzzy C-mean clustering and fuzzy membership algorithm[J]. Energies, 2018, 11(1): 238.
[15] ZHU H L, LU L X, YAO J X, et al.Fault diagnosis approach for photovoltaic arrays based on unsupervised sample clustering and probabilistic neural network model[J]. Solar energy, 2018, 176: 395-405.
[16] XU J Y, WANG W B, GONG T, et al.Fault simulation and characteristic analysis of photovoltaic array[C]//2023 5th Asia Energy and Electrical Engineering Symposium (AEEES). Chengdu, China, 2023: 546-550.
[17] SAKTHIVEL S S, ARUNACHALAM V, JAGATHEESAN K.Detection, classification, and location of open-circuit and short-circuit faults in solar photovoltaic array: an approach using single sensor[J]. IEEE journal of photovoltaics, 2023, 13(6): 986-990.
[18] VAPNIK N.V. Statistical learning theory[M].New York, NY, USA: Wiley-Interscience, 1998, 100-120.
[19] SRINIVAS N, KRAUSE A, KAKADE S M, et al. Gaussian process optimization in the bandit setting: No regret and experimental design[EB/OL].2009: 0912.3995. https://arxiv.org/abs/0912.3995v4.
[20] LI J N, ZHU Q S, WU Q W.A self-training method based on density peaks and an extended parameter-free local noise filter for k nearest neighbor[J]. Knowledge-based systems, 2019, 184: 104895.
[21] LI J N, ZHU Q S, WU Q W, et al.An effective framework based on local cores for self-labeled semi-supervised classification[J]. Knowledge-based systems, 2020, 197: 105804.
[22] LI J N, ZHU Q S.Semi-supervised self-training method based on an optimum-path forest[J]. IEEE access, 2019, 7: 36388-36399.
[23] FRIEDMAN H.J. Greedy function approximation: a gradient boosting machine, Ann. Statist[J]. 2001, 29(5), 1189-1232.
[24] ZHU X J, GHAHRAMANI. Z, LAFFERTY. J.Semi-supervised learning using Gaussian fields and harmonic functions[C]//Proceedings of the Twentieth International Conference on Machine Learning (ICML). Washington DC, USA, 2003: 912-919.