本論文主要針對太陽能系統(Photovoltaic system)直流側的故障提出以卷積神經網路(Convolutional neural network)為基底的運轉狀態監測(Operating condition monitoring)與故障診斷(Fault diagnosis)系統。此系統之特色在於可線上監測經過溫度校正之直流發電比(Ra value)，並顯示即時運轉狀態；一旦發生故障即啟動卷積神經網路為基底的故障診斷器，可辨識開路、線對線、遮蔭以及電弧故障共四種故障型態，其準確率高達近百分之百。該故障診斷器運用由MATLAB/Simulink模擬實際場域而產生之陣列電壓、電流、溫度及照度訊號，做為離線訓練資料。本研究提出之故障診斷系統現場裝設模組電壓量測單元，在發生線對線故障時，可以利用模組電壓資訊，配合直覺式演算法做故障定位，有效降低維修時程與成本。最後，本研究進一步探討故障診斷模組結構、取樣率、雜訊以及模組電壓量測對於故障診斷之影響，其結果可供相關研究參考。

This thesis proposes photovoltaic system operating condition monitoring and fault diagnosis system based on convolutional neural networks for DC side faults. The feature of this system is that it can monitor the temperature-corrected Ra value online, and display the real-time operating condition. Once a fault occurs, it will activate the convolutional neural network-based fault diagnostic program which can identify four types of faults including open circuit, line-to-line, shading and arc fault, and the accuracy is nearly 100%. The program uses the array voltage, array current, temperature and illumination signals generated by MATLAB/Simulink to simulate the actual field as offline training data. The fault diagnosis system proposed in this research has module voltage measurement units. When a line-to-line fault occurs, the module voltage information can be used with an intuitive algorithm to locate the fault, which effectively reduces the maintenance time and cost. Finally, this research further explores the influence of fault diagnosis module structure, sampling rate, noise, and module voltage measurement unit on fault diagnosis. The results can be used as reference for related research.

[1] RENEWABLES 2020 GLOBAL STATUS REPORT, Ren21, Available: https://www.ren21.net/wp-content/uploads/2019/05/gsr_ 2020_full_ report_en.pdf.
[2] Roberto Lacal Arantegui and Arnulf Jäger-Waldau, “Photovoltaics and wind status in the European Union after the Paris Agreement,” Renewable and Sustainable Energy Reviews, Vol. 81, pp. 2460-2471, 2017.
[3] 推動能源轉型，中華民國經濟部，Available: https://www.moea.gov. tw/MNS/populace/Policy/Policy.aspx?menu_id=32800&policy_id=9.
[4] RENEWABLES 2021 GLOBAL STATUS REPORT, Ren21, Available: https://www.ren21.net/wp-content/uploads/2019/05/ GSR2021_Full_ Report.pdf.
[5] Trend in Renewable Energy, IRENA, Available: https://www.irena. org/Statistics/View-Data-by-Topic/Capacity-and-Generation/ Statistics-Time-Series.
[6] IEC Standard 60364-7712, “Electrical Installations of Buildings—Part 7: requirements for special installations or locations—section 712: solar PV power supply systems,” 2002.
[7] IEC Standard 62548, “Installation and safety requirements for PV generators,” 2016.
[8] IEC 61140, “Protection against electric shock Common aspects for installation and equipment,” 2016.
[9] Mohammed Khorshed Alam, Faisal Khan, Jay Johnson and Jack Flicker, “A comprehensive review of catastrophic faults in PV arrays: Types, detection, and mitigation techniques,” IEEE Journal of Photovoltaics, Vol. 5, No. 3, pp. 982-997, 2015.
[10] Zhehan Yi, and Amir H. Etemadi, “Fault detection for photovoltaic systems based on multi-resolution signal decomposition and fuzzy inference systems,” IEEE Transactions on Smart Grid, Vol. 8, No. 3, 2017.
[11] Ye Zhao, Brad Lehman, Jean-Francois de Palma, Jerry Mosesian, Robert Lyons, “Fault analysis in solar PV arrays under: Low irradiance conditions and reverse connections,” IEEE Photovoltaic Specialists Conference, Seattle, USA, Jun. 19-24, 2011, pp. 2000-2005.
[12] Mohammed Khorshed Alam, Faisal H. Khan, Jay Johnson, and Jack Flicker, “PV faults: Overview, modeling, prevention and detection techniques,” IEEE Workshop on Control and Modeling for Power Electronics (COMPEL), Salt Lake City, USA, Jun. 23-26, 2013, pp. 1-7.
[13] Ye Zhao, Jean-Francois de Palma, Jerry Mosesian, Robert Lyons, Jr., and Brad Lehman, “Line-Line fault analysis and protection challenges in solar photovoltaic arrays,” IEEE Transactions on Industrial Electronics, Vol. 60, No. 9, pp. 3784-3795, 2013.
[14] Ward I. Bower and John C. Wiles, “Analysis of grounded and ungrounded photovoltaic systems,” IEEE World Conference on Photovoltaic Energy Conversion (WCPEC), Waikoloa, USA, Dec. 5-9, 1994, pp. 809-812.
[15] Dhanup S. Pillai and N. Rajasekar, “A comprehensive review on protection challenges and fault diagnosis in PV systems,” Renewable and Sustainable Energy Reviews, Vol. 91, pp. 18-40, 2018.
[16] Ground-Fault Analysis and Protection in PV Arrays Tech topics, Mersen, Available: https:// ep-us.mersen.com/ sites/ mersen_us/ files/ 2018-11/TT-PVPN1-Ground-Fault-Analysis-and-Protection-in-PV-Arrays-Tech-Topic.pdf
[17] Indra Man Karmacharya and Ramakrishna Gokaraju, ” Fault location in ungrounded photovoltaic system using wavelets and ANN,” IEEE Transactions on Power Delivery, Vol. 33, No. 2, pp. 549-559, 2018.
[18] J. Prasanth Ram and N. Rajasekar, “A new robust, mutated and fast tracking LPSO method for solar PV maximum power point tracking under partial shaded conditions,” Applied Energy, Vol. 201, pp. 45-49, 2017.
[19] Samantha Chinyoka, Tariro Ncube, Mercy Iroegbu, and Salma M. S. Alarefi , “Partial shading performance evaluation of bifacial PV array configurations,” IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE), Bhubaneswar, India, Dec. 26-27, 2020, pp. 485-488.
[20] Arun PS and Mohanrajan SR, “Effect of partial shading on vehicle integrated PV system,” International conference on Electronics, Communication and Aerospace Technology (ICECA), Coimbatore, India, Jun. 12-14, 2019, pp. 1262-1267.
[21] Katherine A. Kim, Gab-Su Seo, Bo-Hyung Cho, and Philip T. Krein, “Photovoltaic hot-Spot detection for solar panel substrings using AC parameter characterization,” IEEE Transactions on Power Electronics, Vol. 31, No. 2, pp. 1121-1130, 2016.
[22] Yadong Wang, Kazutaka Itako, Tsugutomo Kudoh, Keishin Koh, and Qiang Ge, “Voltage-based hot-Spot detection method for PV string using projector,” IEEE International Conference on Power and Renewable Energy (ICPRE), Shanghai, China, Oct. 21-23, 2016, pp. 570-574.
[23] Jack Flicker and Jay Johnson, “Electrical simulations of series and parallel PV arc-faults,” IEEE Photovoltaic Specialists Conference (PVSC), Tampa, USA, Jun. 16-21, 2013, pp. 3165-3172.
[24] Giuseppe Marco Tina, Fabio Cosentino, and Cristina Ventura, “Monitoring and diagnostics of photovoltaic power plants,” Renewable Energy in the Service of Mankind, Vol 2, pp. 505-516, 2015.
[25] John A. Tsanakas, LongHa, and Claudia Buerhop, “Faults and infrared thermographic diagnosis in operating c-Siphotovoltaic modules: A review of research and future challenges,” Renewable and Sustainable Energy Reviews, Vol. 62, pp. 695-709, 2016.
[26] John A. Tsanakas, Long D. Ha, and F. Al Shakarchi, “Advanced inspection of photovoltaic installations by aerial triangulation and terrestrial georeferencing of thermal/visual imagery,” Renewable Energy, Vol. 102, Part A, pp. 224-233, 2017.
[27] Andreas Livera, Marios Theristis, George Makrides, and George E. Georghiou, “Recent advances in failure diagnosis techniques based on performance data analysis for grid-connected photovoltaic systems,” Renewable Energy, Vol. 133, pp. 126-143, 2018.
[28] Mingyao Ma, Heng Liu, Zhixiang Zhang, Ping Yun , and Fang Liu, “Rapid diagnosis of hot spot failure of crystalline silicon PV module based on I-V curve,” Microelectronics Reliability, Vol. 100-101, No. 1134302, pp. 1-6, 2019.
[29] Takumi Takashima, Junji Yamaguchi, Kenji Otani, Kazuhiko Kato, and Masayoshi Ishida, “Experimental Studies of Failure Detection Methods in PV Module Strings” IEEE World Conference on Photovoltaic Energy Conference, Waikoloa, USA, May 5-12, 2006, pp. 2227-2230.
[30] Sourov Roy, Mohammed Khorshed Alam, Faisal Khan, Jay Johnson, and Jack Flicker, “An irradiance-independent, robust ground-fault detection scheme for PV arrays based on spread spectrum time-domain reflectometry (SSTDR)” IEEE Transactions on Power Electronics, Vol. 33, No. 8, pp. 7046-7057, 2018.
[31] Takumi Takashima, Junji Yamaguchi, Kenji Otani, Takashi Oozeki, Kazuhiko Kato, and Masayoshi Ishida, “Experimental studies of fault location in PV module strings,” Solar Energy Materials and Solar Cells, Vol. 93, No. 6-7, pp. 1079-1082, 2009.
[32] M. Davarifar, A. Rabhi, A. El-Hajjaji, and M. Dahmane, “Real-time model base fault diagnosis of PV panels using statistical signal processing,” International Conference on Renewable Energy Research and Applications (ICRERA), Madrid, Spain, Oct. 20-23, 2013, pp. 599-604.
[33] Silvano Vergura, Giuseppe Acciani, Vitantonio Amoruso, and Giuseppe Patrono, “Inferential statistics for monitoring and fault forecasting of PV plants,” IEEE International Symposium on Industrial Electronics, Cambridge, UK, Jun. 30-Jul. 2, 2008, pp. 2414-2419.
[34] Silvano Vergura, Giuseppe Acciani, Vitantonio Amoruso, Giuseppe E. Patrono, and Francesco Vacca, “Descriptive and inferential statistics for supervising and monitoring the operation of PV plants,” IEEE Transactions on Industrial Electronics, Vol. 56, No. 11, pp. 4456-4464, 2009.
[35] Elyes Garoudja, Fouzi Harrou, Ying Sun, Kamel Kara, Aissa Chouder, and Santiago Silvestre, “Statistical fault detection in photovoltaic systems,” Solar Energy, Vol. 150, pp.485-499, 2017.
[36] D. Stellbogen, “Use of PV circuit simulation for fault detection in PV array fields,” IEEE Photovoltaic Specialists Conference, Louisville, USA, May 10-14, 1993, pp. 1302-1307.
[37] A. Mellit, G.M. Tina, and S.A. Kalogirou, “Fault detection and diagnosis methods for photovoltaic systems: A review,” Renewable and Sustainable Energy Reviews, Vol. 91, pp. 1-17, 2018.
[38] Masaki Miwa, Sanshiro Yamanaka, Hajime Kawamura, Hideyuki Ohno, and Hideaki Kawamura, “Diagnosis of a power output lowering of PV array with a (-dI/dV)-V characteristic,” IEEE World Conference on Photovoltaic Energy Conference, Waikoloa, USA, May 7-12, 2006, pp. 2442-2445.
[39] Wenguan Wang, Alex Chun-For Liu, Henry Shu-Hung Chung, Ricky Wing-Hong Lau, Jun Zhang, and Alan Wai-Lun Lo, “Fault diagnosis of photovoltaic panels using dynamic Current–Voltage characteristics,” IEEE Transactions on Power Electronics, Vol. 31, No. 2, pp. 1588-1599, 2016.
[40] Y. Stauffer, D. Ferrario, E. Onillon, and A. Hutter, “Power monitoring based photovoltaic installation fault detection,” International Conference on Renewable Energy Research and Applications (ICRERA), Palermo, Italy, Nov. 22-25, 2015, pp. 199-202.
[41] Toyonari Shimakage, Kojiro Nishioka, Hiroshi Yamane, Masashi Nagura, and Mitsuru Kudo, “Development of fault detection system in PV system,” IEEE 33rd International Telecommunications Energy Conference (INTELEC), Amsterdam, Netherlands, Oct. 9-13, 2011, pp. 1-5.
[42] Mahmoud Dhimish and Violeta Holmes, “Fault detection algorithm for grid-connected photovoltaic plants,” Solar Energy, Vol. 137, pp. 236-245, 2016.
[43] Adel Mellit and Soteris A. Kalogirou, “Artificial intelligence techniques for photovoltaic applications: A review,” Progress in Energy and Combustion Science, Vol. 34, No 5, pp. 574-632, 2008.
[44] Yuchuan Wu, Qinli Lan, and Yaqin Sun, “Application of BP neural network fault diagnosis in solar photovoltaic system,” International Conference on Mechatronics and Automation, Changchun, China, Aug. 9-12, 2009, pp. 2581-2585.
[45] Andon Coleman and Janusz Zalewski, “Intelligent fault detection and diagnostics in solar plants,” IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems, Prague, Czech Republic, Sep. 15-17, 2011, pp. 948-953.
[46] Pietro Ducange, Michela Fazzolari, Beatrice Lazzerini, and Francesco Marcelloni, “An intelligent system for detecting faults in photovoltaic fields,” International Conference on Intelligent Systems Design and Applications, Cordoba, Spain, Nov. 22-24, 2011, pp. 1341-1346.
[47] Fauzan Hanif Jufri, Seongmun Oh, and Jaesung Jung, “ Development of Photovoltaic abnormal condition detection system using combined regression and Support Vector Machine,” Energy, Vol. 176, pp. 457-467, 2019.
[48] Ye Zhao, Ling Yang, Brad Lehman, Jean-François de Palma, Jerry Mosesian, and Robert Lyons, “Decision tree-based fault detection and classification in solar photovoltaic arrays,” IEEE Applied Power Electronics Conference and Exposition (APEC), Orlando, USA, Feb. 5-9, 2012, pp. 93-99.
[49] Zhicong Chen, Fuchang Han, Lijun Wu, Jinling Yu, Shuying Cheng, Peijie Lin, and Huihuang Chen, “Random forest based intelligent fault diagnosis for PV arrays using array voltage and string currents,” Energy Conversion and Management, Vol. 178, pp. 250-264, 2018.
[50] Guangyu Liu, Ling Zhu, Xinpeng Wua, and Jiajun Wang, “Time series clustering and physical implication for photovoltaic array systems with unknown working conditions,” Solar Energy, Vol. 1, pp. 401-411, 2019.
[51] Ye Zhao, Roy Ball, Jerry Mosesian, Jean-François de Palma, and Brad Lehman, “Graph-based semi-supervised learning for fault detection and classification in solar photovoltaic arrays,” IEEE Transactions on Power Electronics, Vol. 30, No, 5, pp. 2848-2858, 2015.
[52] Honglu Zhu, Lingxing Lu, Jianxi Yao, and Songyuan Dai, “Fault diagnosis approach for photovoltaic arrays based on unsupervised sample clustering and probabilistic neural network model,” Solar Energy, Vol. 176, pp. 395-405, 2018.
[53] A. Belaout, F. Krim, A. Mellit, B. Talbi, and A. Arabi, “Multiclass adaptive neuro-fuzzy classifier and feature selection techniques for photovoltaic array fault detection and classification,” Renewable Energy, Vol. 127, pp. 548-558, 2018.
[54] Soteris Kalogirou and Arzu Sencan, “Artificial intelligence techniques in solar energy applications,” in Solar Collectors and Panels, Theory and Applications, InTech Europe, Croatia, 2010, pp. 315-340.
[55] Guangxin Lou and Hongzhen Shi, “Face image recognition based on convolutional neural network,” China Communications, Vol.17, No. 2, pp. 117-124, 2020.
[56] Basics of the Classic CNN, Towards Data Science, Available: https:// towardsdatascience.com/basics-of-the-classic-cnn-a3dce1225add.
[57] How do Convolutional Neural Networks work?, e2eML school, Available: https://e2eml.school/how_convolutional_neural_networks _work.html.
[58] [資料分析&機器學]第5.1講：卷積神經網絡介紹 (Convolutional Neural Network)，Available: https://medium.com/jameslearningnote/ %E8%B3%87%E6%96%99%E5%88%86%E6%9E%90-E6%A9% 9F%E5%99%A8%E5%AD%B8%E7%BF%92-%E7%AC%AC5-1%E8%AC%9B-%E5%8D%B7%E7%A9%8D%E7%A5%9E% E7%B6%93%E7%B6%B2%E7%B5%A1%E4%BB%8B%E7%B4%B9-convolutional-neural-network-4f8249d65d4f.
[59] Understanding ANN, Rojina Panta, Available: https://rojina99.github. io/understanding_ann/.
[60] Fouzi Harrou, Bilal Taghezouit, and YingSun, “Robust and flexible strategy for fault detection in grid-connected photovoltaic systems,” Energy Conversion and Management, Vol.180, pp. 1153-1166, 2019.
[61] Alivarani Mohapatra, Byamakesh Nayak, and K. B. Mohanty, “Current based novel adaptive P&O MPPT algorithm for photovoltaic system considering sudden change in the irradiance,” IEEE International Conference on Power Electronics, Drives and Energy Systems (PEDES), Mumbai, India, Dec. 16-19, 2014, pp. 1-4.
[62] Muralidhar Killi and Susovon Samanta, “Modified perturb and observe MPPT algorithm for drift avoidance in photovoltaic systems,” IEEE Transactions on Industrial Electronics, Vol. 62, No. 9, pp. 5549-5559, 2015.
[63] Chandra Prabhakar and C.L. Bhattar, “Performance and analysis of PV system at utility level with harmonics mitigation using passive LCL filter,” IEEE International Conference on Intelligent Systems and Control (ISCO), Coimbatore, India, Jan. 9-10, 2015, pp. 1-6.
[64] Darshana R, Chaudhari and Shruti Gour, “PV-Active power filter combination mitigating harmonics using FLC,” 2017 Recent Developments in Control, Automation & Power Engineering (RDCAPE), Noida, India, Oct. 26-27, 2017, pp. 378-381.