PHOTOVOLTAIC MODULE AGING FAULT DIAGNOSIS METHOD BASED ON TIME SERIES FEATURE EXTRACTION

He Yunxiao; Wei Dong; Guo Qian; Gu Xinlei

doi:10.19912/j.0254-0096.tynxb.2023-1049

PDF(2026 KB)

Acta Energiae Solaris Sinica ›› 2024, Vol. 45 ›› Issue (11) : 204-211. DOI: 10.19912/j.0254-0096.tynxb.2023-1049

PHOTOVOLTAIC MODULE AGING FAULT DIAGNOSIS METHOD BASED ON TIME SERIES FEATURE EXTRACTION

He Yunxiao¹, Wei Dong², Guo Qian¹, Gu Xinlei¹

Author information +

History +

Abstract

By analyzing the generation and evolution mechanisms of aging faults and comparing the differences in time-series characteristics among thermal hotspots, micro-cracks, and potential-induced degradation （PID） faults, the unique variation patterns of aging faults in time-series data are determined. By calculating the parameters of the equivalent circuit model of PV string arrays, the influence and correlation of these variation patterns on the model parameters are studied and verified, resulting in the identification of aging fault diagnosis feature vectors. A fuzzy C-means clustering algorithm is employed to propose an aging fault diagnosis method based on time-series feature extraction for PV. Simulation and experimental results demonstrate that the computed model parameters effectively describe the characteristic variations in the time-series data. The identified fault diagnosis features effectively represent the occurrence and evolution processes of aging faults. The proposed fault diagnosis method reliably achieves cause determination, severity classification, and severity estimation of aging faults in PV systems.

Key words

photovoltaic / fault diagnosis / time series / feature extraction / aging / fuzzy C-means clustering

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

He Yunxiao, Wei Dong, Guo Qian, Gu Xinlei. PHOTOVOLTAIC MODULE AGING FAULT DIAGNOSIS METHOD BASED ON TIME SERIES FEATURE EXTRACTION[J]. Acta Energiae Solaris Sinica. 2024, 45(11): 204-211 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1049

References

[1] 叶添翼, 柳翠, 许佳辉, 等. 光伏组件综合序列加速老化测试方法综述[J]. 太阳能, 2022(11): 34-43.
YE T Y, LIU C, XU J H, et al.Overview of comprehensive sequence accelerated aging test methods of PV modules[J]. Solar energy, 2022(11): 34-43.
[2] TANAHASHI T, SAKAMOTON N, SHIBATA H, et al.Corrosion-induced AC impedance elevation in front electrodes of crystalline silicon photovoltaic cells within field-aged photovoltaic modules[J]. IEEE journal of photovoltaics, 2019, 9(3): 741-751.
[3] OH W, BAE S, KIM S, et al.Analysis of degradation in 25-year-old field-aged crystalline silicon solar cells[J]. Microelectronics reliability, 2019, 100: 113392.
[4] HUANG C, WANG L.Simulation study on the degradation process of photovoltaic modules[J]. Energy conversion and management, 2018, 165: 236-243.
[5] PEI T T, HAO X H.A fault detection method for photovoltaic systems based on voltage and current observation and evaluation[J]. Energies, 2019, 12(9): 1712.
[6] 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.
[7] 李智华, 马浩强, 吴春华, 等. 基于三参数的光伏组件老化程度诊断[J]. 中国电机工程学报, 2022, 42(9): 3327-3338.
LI Z H, MA H Q, WU C H, et al.Diagnosing the aging degree of photovoltaic modules based on three parameters[J]. Proceedings of the CSEE, 2022, 42(9): 3327-3338.
[8] 刘强, 郭珂, 毛明轩, 等. 一种基于串联等效电阻的光伏故障检测方法[J]. 太阳能学报, 2020, 41(10): 119-126.
LIU Q, GUO K, MAO M X, et al.A photovoltaic fault detection method based on series equivalent resistance[J]. Acta energiae solaris sinica, 2020, 41(10): 119-126.
[9] 魏缪宇, 卫东, 郭倩, 等. 局部异物遮挡状态下光伏单元输出特性与故障诊断方法[J]. 太阳能学报, 2021, 42(5): 260-266.
WEI M Y, WEI D, GUO Q, et al.Output characteristics and fault diagnosis method of PV unit under partial shading[J]. Acta energiae solaris sinica, 2021, 42(5): 260-266.
[10] LIU Y J, DING K, ZHANG J W, et al.Intelligent fault diagnosis of photovoltaic array based on variable predictive models and I-V curves[J]. Solar energy, 2022, 237: 340-351.
[11] LIU S Y, DONG L, LIAO X Z, et al.Photovoltaic array fault diagnosis based on Gaussian kernel fuzzy C-means clustering algorithm[J]. Sensors, 2019, 19(7): 1520.
[12] LIU G Y, ZHU L, WU X P, et al.Time series clustering and physical implication for photovoltaic array systems with unknown working conditions[J]. Solar energy, 2019, 180: 401-411.
[13] ZHU H L, SHI Y C, WANG H Z, et al.New feature extraction method for photovoltaic array output time series and its application in fault diagnosis[J]. IEEE journal of photovoltaics, 2020, 10(4): 1133-1141.
[14] 戴森柏, 陈志聪, 吴丽君, 等. 利用LSTM和稳态时间序列的光伏阵列故障诊断方法[J]. 福州大学学报(自然科学版), 2022, 50(1): 54-60.
DAI S B, CHEN Z C, WU L J, et al.A photovoltaic array fault diagnosis method using LSTM and steady-state time series[J]. Journal of Fuzhou University (natural science edition), 2022, 50(1): 54-60.
[15] 臧健康, 卫东, 魏缪宇. 基于多峰状态的光伏组串参数求解与波峰最大功率点计算方法[J]. 太阳能学报, 2020, 41(11): 86-94.
ZANG J K, WEI D, WEI M Y.Multi-paek state-based photovolatic string parmater extraction and global maximum power point calculation method[J]. Acta energiae solaris sinica, 2020, 41(11): 86-94.