太陽光電系統運行在環境多變的戶外，容易出現各種類型的故障，若不及時排除，就會出現發電功率損失、元件損壞、熱斑等問題甚至火災事故。在太陽光電系統大規模建設的背景下，及時發現並處置元件故障，提高元件的使用壽命，保持元件的正常運行效率顯得相對重要。
本論文在分析太陽光電陣列電流-電壓(I-V)曲線在不同故障狀態下的差異性的基礎上，以I-V曲線波形、溫度和輻照度為輸入量，提出一種融合卷積神經網路和殘差-門控迴圈單元的太陽光電系統故障識別方法。該方法包括1個有4層結構的一維卷積神經網路單元和1個有殘差的門控迴圈單元。該方法具有端到端故障診斷的特點，不需要人工進行特徵提取，抗幹擾能力強。該方法不僅能識別出單一故障類型，如短路、遮陰、老化等，而且能有效識別出多故障同時存在的情況。該方法對實測資料的診斷準確率達到98.61%，優於人工神經網路、帶核函數的極限學習機、模糊C均值聚類、深度殘差網路模型和SAMME-CART模型。此外，當沒有溫度和輻照度資訊的情況下，準確率依然達到95.23%，所提方法在老舊太陽光電電廠中應用也將具有廣闊的前景。
為解決在併網運行階段的太陽光電系統診斷問題，通過對光電陣列在故障瞬間時序波形變化規律的研究，本文進一步提出一種新型基於時序波形的太陽光電系統故障診斷方法。首先採集故障發生前後的電壓和電流時序波形，通過標準化操作將標準化後的電壓、電流和功率波形作為輸入信號。接著透過堆疊自動編碼器實現故障特徵提取，並提出一種改進的多顆細微性級聯森林(IgcForest)對光電陣列的線-線、開路、遮陰等故障進行診斷。所提方法的優點是利用堆疊自動編碼器自動提取出具有較高辨識度的特徵。利用多顆細微性級聯森林實現故障特徵的增強和挖掘，特別是所提的改進方法在降低特徵向量維度的同時，增強各級森林間資訊連通性，提高診斷的準確率。數值模擬和實測資料對方法的有效性進行了進一步驗證，所提方法對單一類型故障診斷精度分別達到了99.33%和98.61%，優於傳統softmax、支持向量機、隨機森林、多顆細微性級聯森林、層自我調整級聯森林等方法。進一步，當其面對混合故障資料集時，精度依然達到98.83%.
串聯電弧故障是太陽光電發電系統在運行過程中遭遇的危害性最大的故障之一。及時發現串聯電弧故障，避免火災事故的發生，是一項具有挑戰性的工作。針對不同工況下所發生的串聯電弧故障，本文更提出一種結合漢克爾-奇異值分解(Hankel-SVD)降噪和改進經驗小波分解-孿生支持向量機(IEWT-TWSVM)的檢測演算法。該演算法利用漢克爾-奇異值分解演算法對直流母線電流進行去噪，有效避免了開關頻率與無關背景雜訊的影響。隨後將去噪後的電流進行改進經驗小波分解分解，然後將各頻帶的複合多尺度排列熵放入樽海鞘尋優的孿生支持向量機分類器完成故障的檢測。該演算法不僅能夠檢測出不同故障位置的電弧故障，同時還能抵抗動態遮陰、並網、強風等幹擾現象。最後，本研究驗證了模型在電弧暫態過程、長線路故障、單串列系統以及不同取樣速率四種情況下的檢測效果，結果比較理想。實驗表明，所提方法對實測資料的檢測準確率高達98.10%，優於傳統的小波分解、經驗模態分解和統計學(均值、標準差、熵值)等方法。

Since a solar photovoltaic (PV) system operates in the outdoor environment, it is prone to face various types of failures. If failures are not addressed in time, the problems, such as power loss, module damage, hot spots, and even fire accidents, will occur. Under the background of the large-scale construction of solar PV power stations, it is crucial to discover and solve module failures in time for improving the service life and maintaining the normal operation efficiency of modules.
Based on analyzing the difference of current-voltage (I-V) curves of PV arrays under different fault states, the I-V curves, temperatures and irradiances are taken as input data, and a fusion model of convolutional neural network (CNN) and residual-gated recurrent unit (ResGRU) is firstly proposed in this dissertation to identify the PV array fault. This model consists of a one-dimensional CNN module with a four-layer structure and a ResGRU module. It has the advantages of end-to-end fault diagnosis, no manual feature extraction, and strong anti-interference ability. Moreover, it can not only identify a single fault (e.g., short circuit, partial shading, abnormal aging, etc.), but also can effectively identify hybrid faults. Experimental results show that the classification accuracy of this method is 98.61%, which is better than the ones of the artificial neural network (ANN), the extreme learning machine with kernel function (KELM), the fuzzy C-mean (FCM) clustering, the residual neural network (ResNet), and the stage-wise additive modeling using multi-class exponential loss function based on the classification and regression tree (SAMME-CART). In addition, in the absence of temperatures and irradiances, the classification accuracy still reaches 95.23%, which has a broad application prospect in the application of old solar PV power plants.
In order to address the PV fault diagnosis problem in the on-grid operation stage, a novel PV fault diagnostic framework based on the sequence waveform is further investigated in this dissertation by studying the variation rule of PV array at the moment of failure. Firstly, the sequence waveforms of string voltages and currents before and after the fault occurred are collected; the normalized sequence data of voltages, currents, and powers are used as analytic data. Then, the fault feature extraction is realized via a stacked autoencoder (SAE) model. After that, an improved multi-grained cascade forest (IgcForest) is proposed to diagnose faults, e.g., line-to-line (L-L) fault, open-circuit (OC) fault, partial-shading of PV arrays, etc. The advantages of this method are that the SAE method to extract features with higher recognition automatically, and the IgcForest to enhance and exploit fault features. Particularly, the proposed improvements can reduce the feature vector dimension and enhance the information connectivity between forests at all levels for further improving the accuracy of diagnoses. In addition, the validity of this method is verified by numerical simulations and measured data, and the corresponding prcision of fault diagnoses for single failure reach 99.33% and 98.61%, respectively, which are superior to traditional methods, such as softmax, support vector machines, random forest, multi-grained cascade forest, and dense adaptive cascade forest. Furthermore, it also has a high accuracy of 98.83% for data sets with the occurrence of hybrid faults.
Series arc fault (SAF) is one of the most harmful faults during the operation of solar PV systems. It is a challenging task to find SAFs promptly for avoiding the PV fire. Aiming at the SAFs under different operating conditions, a novel detection algorithm by combining the Hankel-singular value decomposition (Hankel-SVD) denoising method and the improved empirical wavelet transform-twin support vector machine (IEWT-TWSVM) is also designed in this dissertation. The Hankel-SVD algorithm is used to denoise the DC-bus current, which alleviates the influence of switching frequency and irrelevant background noise effectively. Then, the denoised current is decomposed by the IEWT, and the composite multiscale permutation entropy (CMPE) of each frequency band is input into the TWSVM classifier of the salp swarm optimization for completing the fault detection. This algorithm not only can detect SAFs at various fault locations, but also resist dynamic shading, inverter startup, strong wind and other interference phenomena. Moreover, the detection performance due to the arc transient process, a long-line fault, a single string array fault, a multiply string array fault and different sampling rates of this model is verified in this dissertation, and the corresponding results are relatively ideal. Experimental results show that the detection accuracy of this method is as high as 98.10% for the measured data which is more superior than other methods, such as wavelet decomposition, empirical mode decomposition, statistics methods including mean, standard deviation, and entropy.

[1] Ren21. (2021, June). Renewables 2021 global status report. REN21. Paris, France. [Online]. Available: https://www.ren21.net/wp-content/uploads/2019/05/GSR_2021 _full_report.pdf.
[2] D.J. Feldman and R.M. Margolis, “Q4 2018/Q1 2019 solar industry update,” United States, doi:10.2172/ 1527335.
[3] J.M. Huang, R.J. Wai and G.J. Yang, “Design of hybrid artificial bee colony algorithm and semi-supervised extreme learning machine for PV fault diagnoses by considering dust impact,” IEEE Trans. Power Electron., vol. 35, no. 7, pp. 7086-7099, July 2020.
[4] M. Cubukcu and A. Akanalci, “Real-time inspection and determination methods of faults on photovoltaic power systems by thermal imaging in Turkey,” Renew. Energy, vol. 147, part A, pp. 1231-1238, Mar. 2020.
[5] A.H. Herraiz, A.P. Marugán, and F.P.G. Márquez, “Photovoltaic plant condition monitoring using thermal images analysis by convolutional neural network-based structure,” Renew. Energy, vol. 153, pp. 334-348, June 2020.
[6] A. Rocky, M. Burhanzoi, O. Kenta, T. Ikegami, and S. Kawai “Photovoltaic module fault detection using integrated magnetic sensors,” IEEE J. Photovolt., vol. 9, no. 6, pp. 1783-1789, Nov. 2019.
[7] Z. Cheng, M. N. Dong, T. K. Yang, and L. J. Han, “Extraction of solar cell model parameters based on self-adaptive chaos particle swarm optimization algorithm,” Trans. Chin. Electr. Soci., vol. 29, no. 9, pp. 245-252, May 2014.
[8] T.T. Pei and X.H. Hao, “A fault detection method for photovoltaic systems based on voltage and current observation and evaluation,” Energies, vol. 12, no. 9, pp. 1-16, Apr. 2019.
[9] N.L. Georgijevic, M.V. Jankovic, S. Srdic, and Z. Radakovic, “The detection of series arc fault in photovoltaic systems based on the arc current entropy,” IEEE Trans. Power Electron., vol. 31, no. 8, pp. 5917-5930, Aug. 2016.
[10] Y. Zhao, J. D. Palma, and J. Mosesian, “Line-line fault analysis and protection challenges in solar photovoltaic arrays,” IEEE Trans. Ind. Electron., vol. 60, no. 9, pp. 3784-3795, Sept. 2013.
[11] R. Hariharan, M. Chakkarapani, G. S. Ilango, and C. Nagamani, “A method to detect photovoltaic array faults and partial shading in PV systems,” IEEE J. Photovolt., vol. 6, no. 5, pp. 1278-1285, Sept. 2016.
[12] D.S. Pillai and N. Rajasekar, “An MPPT-based sensorless line-line and line-ground fault detection technique for PV systems,” IEEE Trans. Power Electron., vol. 34, no. 9, pp. 8646-8659, Sept. 2019.
[13] V.S.B. Kurukuru, F. Blaabjerg, M.A. Khan, and A. Haque, “A novel fault classification approach for photovoltaic systems,” Energies, vol. 12, no. 2, pp. 1-17, Jan. 2020.
[14] S. Yin, J.J. Rodriguez-Andina, and Y.C. Jiang, “Real-time monitoring and control of industrial cyberphysical systems with integrated plant-wide monitoring and control framework,” IEEE Ind. Electron. Mag., vol. 13, no. 4, pp. 38-47, Dec. 2019.
[15] W. Chine, A. Mellit, V. Lughi, A. Malek, G. Sulligoi, and A. M. Pavan, “A novel fault diagnosis technique for photovoltaic systems based on artificial neural networks,” Renew. Energy, vol. 90, pp. 501-512, May 2016.
[16] H.L. Zhu, L.X. Lu, J.X. Yao, S.Y. Dai, and Y. Hu, “Fault diagnosis approach for photovoltaic arrays based on unsupervised sample clustering and probabilistic neural network model,” Sol. Energy, vol. 176, pp. 395-405, Dec. 2018.
[17] Z.C. Chen, F.C. Han, L.J. Wu, J.L. Yu, S.Y. Cheng, P.J. Lin, and H.H. Chen, “Random forest based intelligent fault diagnosis for PV arrays using array voltage and string currents,” Energy Conv. Manag., vol. 178, pp. 250-264, Dec. 2018.
[18] Y.C. Jiang, S. Yin, and O. Kaynak, “Optimized design of parity relation based residual generator for fault detection: data-driven approaches,” IEEE Trans. Ind. Inform., vol.17, no.2, pp.1449-1458, Feb. 2021.
[19] Y.K. Wu, B. Jiang, and N.Y. Lu, “A descriptor system approach for estimation of incipient faults with application to high-speed railway traction devices,” IEEE Trans. Syst., Man, Cybern.: Syst., vol. 49, no. 10, pp. 2108-2118, Oct. 2019.
[20] 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,” Renew. Energy, vol. 127, pp. 548-558, Nov. 2018.
[21] Z. C. Chen, L. J. Wu, S. Y. Cheng, P. J. Lin, Y. Wu, and W. Lin, “Intelligent fault diagnosis of photovoltaic arrays based on optimized kernel extreme learning machine and I-V characteristics,” Appl. Energy, vol. 204, pp. 912-931, Oct. 2017.
[22] F.H. Jufri, S.M. Oh, and J.S. Jung, “Development of photovoltaic abnormal condition detection system using combined regression and support vector machine,” Energy, vol. 176, pp. 457-467, June 2019.
[23] Y.K. Wu, B. Jiang, and Y.L. Wang, “Incipient winding fault detection and diagnosis for squirrel-cage induction motors equipped on CRH trains,” ISA Trans., vol. 99, pp. 488-495, Apr. 2020.
[24] X.Y. Lu, P.J. Lin, S.Y. Cheng, Y.H. Lin, Z.C. Chen, L.J. Wu, and Q.Y. Zheng, “Fault diagnosis for photovoltaic array based on convolutional neural network and electrical time series graph,” Energy Conv. Manag., vol. 196, pp. 950-965, Sept. 2019.
[25] Z. C. Chen, Y.X. Chen, L.J. Wu, S.Y. Cheng, and P.J. Lin, “Deep residual network based fault detection and diagnosis of photovoltaic arrays using current-voltage curves and ambient conditions,” Energy Conv. Manag., vol. 198, pp. 1-20, Oct. 2019.
[26] S.B. Lu, T. Sirojan, B.T. Phung, and E. Ambikairajah, “DA-DCGAN: An effective methodology for DC series arc fault diagnosis in photovoltaic systems,” IEEE Access, vol. 7, pp. 45831-45840, Apr. 2019.
[27] X.Y. Tang, B. Du, J.Z. Huang, Z.M. Wang, and L.F. Zhang, “On combining active and transfer learning for medical data classification,” IET Comput. Vis., vol. 13, no. 2, pp. 194-205, Feb. 2019.
[28] Q. Xiong, X.J. Liu, X.Y. Feng, A.L. Gattozzi, Y.H. Shi, L.Y. Zhu, S.C. Ji, and R.E. Hebner, “Arc fault detection and localization in photovoltaic systems using feature distribution maps of parallel capacitor currents,” IEEE J. Photovolt., vol.8, no.4, pp.1090-1097, June 2018.
[29] National Electrical Code(R) (NEC) Edition, NFPA70, Nat. Fire Protection Assoc., Quincy, MA, USA, 2014.
[30] S. Dhar, R. K. Patnaik, and P. K. Dash, “Fault detection and location of photovoltaic based DC microgrid using differential protection strategy,” IEEE Trans. Smart Grid, vol. 9, no. 5, pp. 4303-4312, Sept. 2018.
[31] S.B. Lu, B.T. Phung, and D. Zhang, “A comprehensive review on DC arc faults and their diagnosis methods in photovoltaic systems,” Renew. Sust. Energ. Rev., vol. 89, pp. 88-98, June 2018.
[32] Q. Lu, Z. Ye, M. Su, Y. Li, Y. Sun, and H. Huang, “A DC series arc fault detection method using line current and supply voltage,” IEEE Access, vol. 8, pp. 10134-10146, Jan. 2020.
[33] S. Chen, Q. Lv, Y. Meng, X. Li, and N. Xu, “Hardware implementation of series arc fault detection algorithm for different DC resistive systems,” in 2019 IEEE Holm Conf. Electrical Contacts, Milwaukee, WI, USA, 2019, pp. 245-249.
[34] M. Ahmadi, H. Samet, and T. Ghanbari, “Series arc fault detection in photovoltaic systems based on signal-to-noise ratio characteristics using cross-correlation function,” IEEE Trans. Ind. Inform., vol. 16, no. 5, pp. 3198-3209, May 2020.
[35] S. Chae, J. Park, and S. Oh, “Series DC arc fault detection algorithm for DC microgrids using relative magnitude comparison,” IEEE J. Emerg. Sel. Top. Power Electron., vol. 4, no. 4, pp. 1270-1278, Dec. 2016.
[36] H. Zhu, Z. Wang, and R. S. Balog, “Real time arc fault detection in PV systems using wavelet decomposition,” in 2016 IEEE 43rd Photovoltaic Specialists Conf.(PVSC), Portland, OR, 2016, pp. 1761-1766.
[37] K. Xia, S. He, Y. Tan, Q. Jiang, J.J. Xu, and W. Yu, “Wavelet packet and support vector machine analysis of series DC arc fault detection in photovoltaic system,” IEEJ Trans. Electr. Electron. Eng., vol. 14, no. 2, pp. 192-200, Feb. 2019.
[38] S. Liu, L. Dong, X. Liao, X. Cao, X. Wang, and B. Wang, “Application of the variational mode decomposition-based time and time-frequency domain analysis on series DC arc fault detection of photovoltaic arrays,” IEEE Access, vol. 7, pp. 126177-126190, Sep. 2019.
[39] W. Miao, Q. Xu, K.H. Lam, P.W.T. Pong, and H.V. Poor, “DC arc-fault detection based on empirical mode decomposition of arc signatures and support vector machine,” IEEE Sens. J., vol. 21, no. 5, pp. 7024-7033, Mar. 2021.
[40] C.H Wu, W.X. Xu, Z.H. Li, L.J. Xu, and T.Y. Bai, “Study on detection method and its anti-interference of dc arc fault for photovoltaic system,” Proc. CSEE, vol. 38, no. 12, pp. 3546-3555, Jan. 2018.
[41] R.D. Telford, S. Galloway, B. Stephen, and I. Elders, “Diagnosis of series DC arc faults—A machine learning approach,” IEEE Trans. Ind. Inform., vol. 13, no. 4, pp. 1598-1609, Aug. 2017.
[42] A. Khamkar and D.D. Patil, “Arc fault and flash signal analysis of DC distribution system sing artificial intelligence,” in 2020 Int. Conf. Renewable Energy Integration into Smart Grids: A Multidisciplinary Approach to Technology Modelling and Simulation (ICREISG), Bhubaneswar, India, 2020, pp. 10-15.
[43] Q. Xiong, S. Ji, L. Zhu, L. Zhong, and Y. Liu, “A novel DC arc fault detection method based on electromagnetic radiation signal,” IEEE Trans. Plasma Sci., vol. 45, no. 3, pp. 472-478, Mar. 2017.
[44] M.K. Alam, F.H. Khan, J. Johnson, and J. Flicker, “PV arc-fault detection using spread spectrum time domain reflectometry (SSTDR),” in 2014 IEEE Energy Conversion Congress and Exposition (ECCE), Pittsburgh, PA, 2014, pp. 3294-3300.
[45] T. Esram and P.L. Chapman, “Comparison of photovoltaic array maximum power point tracking techniques,” IEEE Trans. Energy Conv. Manag., vol. 22, no. 2, pp.439-449, Jun. 2007.
[46] E. Kim, “A fuzzy disturbance observer and its application to control,” IEEE Trans. Fuzzy Syst., vol. 10, no. 1, pp.77-84, Feb. 2002.
[47] E.A. Silva, F. Bradaschia, M.C. Cavalcanti, A.J. Nascimento, L. Michels, and L.P. Oietta, “An eight-parameter adaptive model for the single diode equivalent circuit based on the photovoltaic module's physics,” IEEE J. Photovolt., vol. 7, no. 4, pp. 1115-1123, July 2017.
[48] E. Moshksar and T. Ghanbari, “Adaptive estimation approach for parameter identification of photovoltaic modules,” IEEE J. Photovolt., vol. 7, no. 2, pp. 614-623, Mar. 2017.
[49] S. Spataru, D. Sera, T. Kerekes, and R. Teodorescu, “Diagnostic method for photovoltaic systems based on light I–V measurements,” Sol. Energy, vol. 119, pp. 29-44, July 2015.
[50] W. Gao and R. J. Wai, “A novel fault identification method for photovoltaic array via convolutional neural network and residual gated recurrent unit,” IEEE Access, vol. 8, pp. 159493-159510, Aug. 2020.
[51] J. M. Huang, R. J. Wai, and W. Gao, “Newly-designed fault diagnostic method for solar photovoltaic generation system based on IV-curve measurement,” IEEE Access, vol. 7, pp. 70919-70932, May 2019.
[52] W. Gao, R. J. Wai, and S. Q. Chen, “Novel PV fault diagnoses via SAE and improved multi-grained cascade forest with string voltage and currents measures,” IEEE Access, vol. 8, pp. 133144-133160, July 2020.
[53] S.Y. Liu, L. Dong, X.Z. Liao, Y. Hao, X.D. Cao, and X.X. Wang, “A dilation and Erosion-based clustering approach for fault diagnosis of photovoltaic arrays,” IEEE Sens. J., vol. 19, no.11, pp. 4123-4137, June 2019.
[54] Y. Mahmoud and E.F. El-saadany, “Enhanced reconfiguration method for reducing mismatch losses in PV systems,” IEEE J. Photovolt., vol. 7, no. 6, pp. 1746-1754, Nov. 2017.
[55] Y. Zhao, B. Lehman, J.F.D. Palma, J. Mosesian, and R. Lyons, “Challenges of overcurrent protection devices in photovoltaic arrays brought by maximum power point tracker,” in 2011 37th IEEE Photovoltaic Specialists Conf., pp.2472-2477, June 2011.
[56] M. Ahmadi, H. Samet, and T. Ghanbari, R. Zhao, D. Wang, R. Yan, K. Mao, F. Shen, and J. Wang, “A new method for detecting series arc fault in photovoltaic systems based on the blind-source separation,” IEEE Trans. Ind. Electron., vol. 67, no. 6, pp. 5041-5049, June 2020.
[57] W. Gao and R. J. Wai, “Series arc fault detection of grid-connected PV system via SVD denoising and IEWT-TWSVM,” IEEE J. Photovolt., vol. 11, no. 6, pp. 1493-1510, November 2021.
[58] V. Le, X. Yao, C. Miller, and B. Tsao, “Series DC arc fault detection based on ensemble machine learning,” IEEE Trans. Power Electron., vol. 35, no. 8, pp. 7826-7839, Aug. 2020.
[59] D.D. Peng, Z.L. Liu, H. Wang, Y. Qin, and L.M. Jia, “A novel deeper one-dimensional CNN with residual learning for fault diagnosis of wheelset bearings in high-speed trains,” IEEE Access, vol. 7, pp. 10278 -10293, Dec. 2018.
[60] G.P. Liao, W. Gao, G.J. Yang, and M.F. Guo, “Hydroelectric generating unit fault diagnosis using 1-D convolutional neural network and gated recurrent unit in small hydro,” IEEE Sensor J., vol. 19, no. 20, pp. 9352-9363, Oct. 2019.
[61] P. Poomka, W. Pongsena, N. Kerdprasop, and K. Kerdprasop, “SMS spam detection based on long short-term memory and gated recurrent unit,” Int. J. Fut. Comp. & Comm., vol. 8, no. 1, pp. 11-15, Mar. 2019.
[62] S. Kiranyaz, T. Ince, and M. Gabbouj, “Real-time patient-specific ECG classification by 1-D convolutional neural networks,” IEEE Trans. Biom. Eng., vol. 63, no. 3, pp. 664-675, Mar. 2016.
[63] T. Ince, S. Kiranyaz, L. Eren, M. Askar, and M. Gabbouj, “Real-time motor fault detection by 1-D convolutional neural networks,” IEEE Trans. Ind. Electr., vol. 63, no. 11, pp. 7067-7075, Nov. 2016.
[64] R. Zhao, D. Wang, R. Yan, K. Mao, F. Shen, and J. Wang, “Machine health monitoring using local feature-based gated recurrent unit networks,” IEEE Trans. Ind. Electron., vol. 65, no. 2, pp. 1539-1548, Feb. 2018.
[65] K. Cho, B.V. Merrienboer, C. Gulcehre C, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using RNN encoder-decoder for statistical machine translation,” Technical Report (Cornell University), arXiv: 1406.1078v3, pp. 1-15, Sept. 2014.
[66] K. Cho, B.V. Merrienboer, D. Bahdanau, and Y. Bengio, “On the properties of neural machine translation: encoder-decoder approaches,” Technical Report (Cornell University), arXiv: 1409.1259v2, pp. 1-9, Oct. 2014.
[67] K.M. He, X.Y. Zhang, S.Q. Ren, and J. Sun, “Deep residual learning for image recognition,” Proc. IEEE Conf. Comp. Vision Patt. Recogn., pp. 770-778, 2016.
[68] B. Ahmed, T.A. Gulliver, and S. Alzahir, “Image splicing detection using mask-RCNN,” Signal Image Video Process., vol. 14, no. 5, pp. 1035-1042, Jan. 2020.
[69] S.N. Zeng, J.P. Gou, and L.M. Deng, “An antinoise sparse representation method for robust face recognition via joint L1 and L2 regularization,” Expert Syst. Appl., vol. 82, no. 1, pp. 1-9, Oct. 2017.
[70] L.V.D. Maaten and G. Hinton. “Visualizing data using t-SNE,” J. Mach. Learn. Res., vol. 9, pp. 2579-2605, Nov. 2008.
[71] Y.G. Lei, F. Jia, J. Lin, S.B. Xing, and S.X. Ding, “An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data,” IEEE Trans. Ind. Electron., vol. 63, no. 5, pp. 3137-31, Jan. 2016.
[72] Z. Zhao, J. Li, L. Wang, D. Wei, and K. Gao, “Signal-to-noise ratio improvement of MAMR on CoX/Pt media,” IEEE Trans. Magn., vol. 51, no. 11, pp. 1-4, Nov. 2015.
[73] B.J. Li, C. Delpha, A. Migan-Dubois, and D. Diallo, “Fault diagnosis of photovoltaic panels using full I–V characteristics and machine learning techniques,” Energy Conv. Manag., vol. 248, pp. 1-13, Nov. 2021.
[74] P.K. Ray, A. Mohanty, B.K. Panigrahi, and P.K. Rout, “Modified wavelet transform based fault analysis in a solar photovoltaic system,” Optik, vol. 168, pp. 754-763, Sept. 2018.
[75] H. C. Shin, M. Orton, D. J. Collins, S. Doran and M. O. Leach, “Autoencoder in time-series analysis for unsupervised tissues characterisation in a large unlabelled medical image dataset,” 10th Int. Conf. Mach. Learn. Appl. Worksh., vol. 1, pp. 259-264, 2011.
[76] J. Xu, L. Xiang, R. Hang and J. Wu, “Stacked sparse autoencoder (SSAE) based framework for nuclei patch classification on breast cancer histopathology,” IEEE Int. Conf. Sympos. Biomed. Imag., pp. 999-1002, 2014.
[77] Z. H. Zhou and J. Feng, “Deep forest,” Natl. Sci. Rev., vol. 6, no.1, pp.74-86, Jan. 2019.
[78] H. Y. Wang, Y.Tang, Z. Y. Jia, and F. Ye, “Dense adaptive cascade forest: a self-adaptive deep ensemble for classification problems,” Soft Comp., vol. 24, pp.2955-2968, Feb. 2020.
[79] H.H. Cho, Y.J. Kim, E.J. Lee, D.Y. Choi, Y.J. Lee, and W.J. Rhee, “Basic enhancement strategies when using Bayesian optimization for hyperparameter tuning of deep neural networks”, IEEE Access, vol. 8, pp. 52588-52608, Mar. 2020.
[80] C.J. Willmott and K. Matsuura, “Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance,” Clim. Res., vol. 30, no. 1, pp.79-82, Dec. 2005.
[81] L. L. C. Kasun, Y. Yang, G. Huang, and Z. Zhang, “Dimension reduction with extreme learning machine,” IEEE Trans. Image Process., vol. 25, no. 8, pp. 3906-3918, Aug. 2016.
[82] G.B. Huang, D.H. Wang, and Y. Lan, “Extreme learning machines: a survey,” Int. J. Mach. Learn. & Cyber., vol. 2, pp.107-122, May 2011.
[83] Z. Yang, X. Wang, and P. K. Wong, “Single and simultaneous fault diagnosis with application to a multistage gearbox: a versatile dual-ELM network approach,” IEEE Trans. Ind. Inform., vol. 14, no. 12, pp. 5245-5255, Dec. 2018.
[84] M.F. He, Y.G. Zhou, Y. Li, G.F. Wu, and G. Tang, “Long short-term memory network with multi-resolution singular value decomposition for prediction of bearing performance degradation,” Meas., vol.156, pp.1-9, May 2020.
[85] Y.G. Yue, T. Jiang, C. Han, J.Y. Wang, Y.F. Chao, and Q. Zhou, “Suppression of periodic interference during tunnel seismic predictions via the Hankel-SVD-ICA method,” J. Appl. Geophys., vol. 168, pp. 107-117, Sept. 2019.
[86] J. Gilles, “Empirical wavelet transform,” IEEE Trans. Signal Process., vol. 61, no. 16, pp. 3999-4010, Aug. 2013.
[87] A.Q. Zhang, T.Y. Ji, M.S. Li, Q.H. Wu, and L.L. Zhang, “An identification method based on mathematical morphology for sympathetic inrush,” IEEE Trans. Power Deliv., vol. 33, no. 1, pp. 12-21, Feb. 2018.
[88] M. Salehi and F. Namdari, “Fault location on branched networks using mathematical morphology,” IET Gener. Transm. Distrib., vol. 12, no. 1, pp. 207-216, Jan. 2018.
[89] S. Nalband, A. Prince, and A. Agrawal, “Entropy-based feature extraction and classification of vibroarthographic signal using complete ensemble empirical mode decomposition with adaptive noise,” IET Sci. Meas. Technol., vol. 12, no. 3, pp. 350-359, May 2018.
[90] X.J. Chen, Y.M. Yang, Z.X. Cui, and J. Shen, “Wavelet denoising for the vibration signals of wind turbines based on variational mode decomposition and multiscale permutation entropy,” IEEE Access, vol. 8, pp. 40347-40356, Feb. 2020.
[91] Z.Q. Huo, Y. Zhang, L. Shu, and M. Gallimore, “A new bearing fault diagnosis method based on fine-to-coarse multiscale permutation entropy, Laplacian score and SVM,” IEEE Access, vol. 7, pp. 17050-17066, Jan. 2019.
[92] Jayadeva, R. Khemchandani, and S. Chandra, “Twin support vector machines for pattern classification,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 29, no. 5, pp. 905-910, May 2007.
[93] S. Mirjalili, A.H. Gandomi, S.Z. Mirjalili, S. Saremi, H. Faris, and S.M. Mirjalil, “Salp swarm algorithm: a bio-inspired optimizer for engineering design problems,” Adv. Eng. Softw., vol. 114, pp. 163-191, Dec. 2017.
[94] W.B. Zhang, J.X. Zhu, Y.S. Pu, and J. Min, “Application of Singular Value Energy Difference Spectrum in Axis Trace Refinement,” Sens. & Transd., vol.167, no. 3, Mar., 2014.
[95] I. Jebli, F. Belouadha, M.I. Kabbaj, and A. Tilioua, “Prediction of solar energy guided by Pearson correlation using machine learning,” Energy, vol. 224, June 2021.
[96] Z.H. Zhan, J. Zhang, Y. Li, and H.S.H. Chung, “Adaptive particle swarm optimization,” IEEE Trans. Syst., Man, & Cybern., Part B (Cybern.), vol. 39, no. 6, pp. 1362-1381, Dec. 2009.
[97] H. Wei and X.S. Tang, “A genetic-algorithm-based explicit description of object contour and its ability to facilitate recognition,” IEEE Trans. Cybern., vol. 45, no. 11, pp. 2558-2571, Nov. 2015.
[98] Jayadeva, R. Khemchandani, and S. Chandra, “Twin support vector machines for pattern classification,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 29, no. 5, pp. 905-910, May 2007.
[99] Q. Zhao, S. Shao, L.X. Lu, X. Liu, and H.L. Zhu, “A new PV array fault diagnosis method using fuzzy C-mean clustering and fuzzy membership algorithm,” Energies, vol.11, no. 1, pp.1-21, Jan. 2018.
[100] B. P. Kumar, G. S. Ilango, M. J. B. Reddy, and N. Chilakapati, “Online fault detection and diagnosis in photovoltaic systems using wavelet packets,” IEEE J. Photovolt., vol. 8, no. 1, pp. 257-265, Jan. 2018.
[101] Z. Yi and A. H. Etemadi, “Line-to-line fault detection for photovoltaic arrays based on multiresolution signal decomposition and two-stage support vector machine,” IEEE Trans. Ind. Electron., vol. 64, no. 11, pp. 8546-8556, Nov. 2017.
[102] A. Khoshnami and I. Sadeghkhani, “Sample entropy-based fault detection for photovoltaic arrays,” IET Renew. Power Gener., vol. 12, no. 16, pp. 1966-1976, Dec. 2018.
[103] S.L. Chen, X.W. Li, Y. Meng, and Z.M. Xie, “Wavelet-based protection strategy for series arc faults interfered by multicomponent noise signals in grid-connected photovoltaic systems,” Sol. Energy, vol. 183, pp. 327-336, May 2019.
[104] Standard, U. L. “Outline of investigation for photovoltaic (PV) DC arc-fault circuit protection,” Standard 1699B, (2018).
[105] C.H. Wu, W.X. Xu, Z.H. Li, and L.J. Xu, “Arc fault type identification and circuit protection in photovoltaic system,” Proc. CSEE, vol.37, no.17, pp.5028-5036, Sept. 2017.
[106] A. Omazic, G. Oreski, M. Halwachs, G.C. Eder, C. Hirschl, L. Neumaier, G. Pinter, and M. Erceg, “Relation between degradation of polymeric components in crystalline silicon PV module and climatic conditions: A literature review,” Sol. Energy Mat. Solar Cells, vol. 92, pp. 123-133, April. 2019.
[107] W. Gao, S. P. Qiao, R. J. Wai, and M. F. Guo, “A newly-designed diagnostic method for mechanical faults of high-voltage circuit breakers via SSAE and IELM,” IEEE Trans. Instr. & Meas., vol. 70, pp.1-13, July 2020.
[108] M.U. Saleh, C. Deline, S. Kingston, N.K.T. Jayakumar, E. Benoit, J. B. Harley, C. Furse, and M. Scarpulla, "Detection and localization of disconnections in PV strings using spread-spectrum time-domain reflectometry," IEEE J. Photovolt., vol. 10, no. 1, pp. 236-242, Jan. 2020.
[109] I. M. Karmacharya and R. Gokaraju, "Fault location in ungrounded photovoltaic system using wavelets and ANN," IEEE Trans. Power Deliv., vol. 33, no. 2, pp. 549-559, April 2018.