跳到主要內容

臺灣博碩士論文加值系統

(44.222.64.76) 您好!臺灣時間:2024/06/17 09:06
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:洪子逸
研究生(外文):PULA , ROLANDO ADVINCULA
論文名稱:通過深度學習和帶有 LoRa 通知系統的數位孿生進行光伏故障診斷
論文名稱(外文):Photovoltaic Fault Diagnosis through Deep Learning and Digital Twin with LoRa Notification System
指導教授:洪穎怡洪穎怡引用關係
指導教授(外文):Hong Ying-Yi
口試委員:劉志文張宏展張文恭楊宏澤朱家齊
口試委員(外文):ZHI-WEN LIUHONG-ZHAN ZHANGWEN-GONG ZHANGHONG-ZE YANGJIA-QI ZHU
口試日期:2023-05-25
學位類別:博士
校院名稱:中原大學
系所名稱:電機工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2023
畢業學年度:111
語文別:英文
論文頁數:135
中文關鍵詞:診斷卷積神經網路數位孿生馬可夫過渡場
外文關鍵詞:DiagnosisConvolutional Neural NetworkDigital TwinMarkov Transition FieldPhotovoltaics
DOI:10.6840/cycu202301199
ORCID或ResearchGate:https://scholar.google.com/citations?user=1yj9GCwAAAAJ&hl=en
https://orcid.org/0000-0002-8914-0434
https://www.researchgate.net/profile/Rolando-Pula
相關次數:
  • 被引用被引用:0
  • 點閱點閱:57
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
光伏系統已成為再生能源的主要來源,近年來它們的產量迅速增長。為防止光伏故障導致電能和財務的損失,本文提出了一種診斷併網型光伏陣列故障的方法。該方法包括三個階段:第一階段使用數位孿生檢測故障,第二階段使用ConvMixer深度學習方法對故障進行分類,第三階段使用LoRa(長距離)系統通知故障。數位孿生是一個虛擬模型,透過照度和溫度可以準確反映物理光伏陣列的行為和特徵。ConvMixer是一種新的深度學習方法,使用光伏直流陣列功率生成的2D圖像,它在分類故障方面優於傳統機器學習和卷積神經網路方法。LoRa通知系統適用於低功耗廣域網路,通常用於大型光伏電場。本論文使用即時數位模擬器驗證,證明了數位孿生、ConvMixer和LoRa通知系統的整合具有即時適用性。
Photovoltaics, which is increasing rapidly, is one of main renewable power resources. For mitigating financial and energy losses, a novel method has been developed in this dissertation for diagnosing faults in grid-connected PV arrays. The method consists of three phases: fault detection using the Digitla Twin (DT), fault classification using the ConvMixer deep learning (DL) approach, and fault notification through a long-range (LoRa) communication system. The virtual DT accurately reflects the characteristics and behavior of a physical PV array using input irradiance and temperature. The ConvMixer deep learning model utilizes the 2D images generated from PV DC array power to classify faults, outperforming traditional machine learning and convolutional neural network methods. The LoRa notification system, suitable for low-power wide-area networks commonly used in large PV farms, is used to notify faults. The proposed method has been verified using a real-time digital simulator, demonstrating real-time applicability for integrating the DT, ConvMixer, and LoRa notification system.
摘要 I
Abstract II
Acknowledgements III
Table of Contents IV
List of Figures VII
List of Tables IX
Chapter 1: Introduction 1
1-1 Background of the Study 1
1-2 Literature Review 2
1-3 Problem Statement and Challenges 7
1-4 Contributions of Dissertation 8
1-5 Scope and Delimitation 10
1-6 Structure of Dissertation 11
Chapter 2: Photovoltaic System 13
2-1 Grid-Connected PV System 13
2-2 Components of Grid-Connected PV System 13
2-3 Photovoltaic Cells, Modules, Arrays 15
2-4 DC/DC Boost Converter 20
2-5 DC/AC Inverter 23
2-6 Three-Phase Transformer 24
2-7 Protection Devices 25
2-8 Studied PV System 27
Chapter 3: Types of PV Fault and Partial Shading Conditions 29
3-1 Brief Introduction 29
3-2 Line-to-line Fault 30
3-3 Open-Circuit Fault (Open Module and Open String) 31
3-4 Shorted-Circuit Fault (Shorted Module and Shorted String) 31
3-5 Partial Shading Conditions 32
3-6 Degradation Faults 32
3-7 Arc Faults 34
Chapter 4: Background of Methods 35
4-1 Signal to 2D Image Transformation 35
4-1-1 Markov Transition Field Transformation 35
4-1-2 Recurrence Plot 36
4-1-3 Gramian Angular Field (GAF) Transformation 37
4-2 Digital Twin Concept 38
4-3 Convolutional Mixer 39
4-3-1 Types of Convolutions 42
4-3-2 Vision Transformer 48
4-3-2-1 Patch Embeddings 50
4-3-2-2 Positional Embeddings 51
4-3-2-3 Multi-Layer Perceptron 52
4-3-2-4 Batch Normalization 52
4-3-2-5 Global Average Pooling 57
4-3-3 The Standard Transformer 60
4-3-3-1 Stacked Encoder Decoder 60
4-3-3-2 Attention Mechanism 62
4-4 Long-Range Applications 64
4-3-1 LoRa and LoRaWAN 67
4-3-2 LoRa and Radio Modulation 70
4-3-3 Modulation Properties of LoRA 73
4-3-3 Modulation Characteristics of LoRA 74
4-3-4 Collisions of Data and Orthogonality of Spreading Factor 76
4-3-4 LoRaWAN Gateway 77
4-3-4 Network Server 78
4-3-5 Application Server 79
4-3-6 Join Server 80
4-3-7 LoRaWAN Network Elements: Device Commissioning and Security 80
4-3-8 LoRa End Device Class 81
Chapter 5: Methodology 83
5-1 Conceptual Framework of the Study 83
5-2 The Studied PV System 84
5-3 PV Fault Detection Using Digital Twin 85
5-4 Classification of Fault Using ConvMixer 87
5-4-1 Application of MTF for Image Transformation 88
5-4-2 Development of ConvMixer 88
5-4-3 LoRa Notification System for Detected and Classified Fault 90
Chapter 6: Simulation Results and Discussions 92
6-1 Dataset 92
6-2 Results Obtained From Digital Twin 95
6-3 Results of PV Fault Classification Using ConvMixer 96
6.4 LoRa Notification System Settings 99
6.5 Comparison with Other PV Fault Classification Methods 106
6.6 Digital Real-time Simulation 109
Chapter 7: Conclusion and Future Works 113
7.1 Conclusion 113
7.2 Future Works 114
References 115


List of Figures
Figure 2- 1 Typical Grid-Connected PV [48]..............................................................14
Figure 2- 2 Electric Field Effect in PV Cell [49].........................................................16
Figure 2- 3 Illustration of PV cell, module, panel, and arrays [49]. ............................17
Figure 2- 4 Solar cell Equivalent circuit......................................................................17
Figure 2- 5 (a) I-V and (b) P-V Characteristic Curves of PV Panel [52]. ...................19
Figure 2- 6 The I-V Characteristic, P-V Characteristic, and MPP Levels of PV Cell at
Different Levels of Irradiance and Temperature [49]..................................................20
Figure 2- 7 (a) Illustration of DC-DC Boost Converter, (b) Mode 1and Mode 2
Operation of DC-DC Boost Converter, (c) Boost Converter Waveforms during CCM,
(d) Boost Converter Waveforms during DCM [53].....................................................21
Figure 2- 8 Process Flowchart of P&O Algorithm [54]. .............................................22
Figure 2- 9 3-phase Full-Bridge VSI Illustration.........................................................24
Figure 2- 10 Studied Grid-Connected PV System Topology ......................................28
Figure 3- 1 Typical Faults in PV System.....................................................................29
Figure 4- 1 The equivalent DT implemented in this work [16]...................................39
Figure 4- 2 The architecture of Convolutional-Mixer [70]..........................................42
Figure 4- 3 Illustration of Convolution Operation in which Number of Convolution
Equals to One...............................................................................................................44
Figure 4- 4 Illustration of Convolution in which Number of Convolutions Equals to
64..................................................................................................................................44
Figure 4- 5 Illusration of Depthwise Convolution Operation......................................45
Figure 4- 6 Illustration of Pointwise Convolution in which Number of Convolution
Equals to One...............................................................................................................46
Figure 4- 7 Illustration of Pointwise Convolution with Number of Kernel Equals to
64..................................................................................................................................47
Figure 4- 8 The Standard Vision Transformer Architecture [73]. ...............................49
Figure 4- 9 Illustration of Image Representation Into Sequence of Flattened Patches.
......................................................................................................................................50
Figure 4- 10 Illustration of Patch Emebedding [74]....................................................51
Figure 4- 11 Patch Embedding and Positional Embedding [74]..................................51
Figure 4- 12 Illustration of (a) Linear Convolution layer (b) Mlpconv Layer.............58
Figure 4- 13 The Standard Transformer Pre.sented in [78]. ........................................61
Figure 4- 14 Two Types of Attention Presented in [77]..............................................63
Figure 4- 15 Typical LoRAWAN Topology [71]........................................................66
Figure 4- 16 LoRAWAN Network Deployment Advantages [81]..............................69
Figure 4- 17 The 7-layer OSI Model [81]....................................................................70
Figure 4- 18 Signal Changes in DSSS System Carrier Phase [81]..............................71
Figure 4- 19 Illustration of LoRA CSS [81]. ...............................................................72
Figure 5- 1 Proposed over-all PV fault diagnosis framework .....................................83
Figure 5- 2 Illustration of studied PV system. .............................................................84
Figure 5- 3 Illustration of MTF in generation of 1D signal to 2D images...................88
Figure 5- 4 The structure of the ConMixer use in this work. ......................................90
Figure 6-1 (1) 2D images line-to-line fault equivalent with various percentage of
mismatches...................................................................................................................93
Figure 6-1 (2) 2D images open-module fault equivalent with various percentage of
mismatches...................................................................................................................93
Figure 6-1 (3) 2D images open-string fault equivalent with various percentage of
mismatches...................................................................................................................93
Figure 6-1( 4) 2D images shorted-string fault equivalent with various percentage of
mismatches...................................................................................................................93
Figure 6-1 (5) 2D images shorted-module fault equivalent with various percentage of
mismatches...................................................................................................................94
Figure 6-1 (6)2D images partial shading conditions equivalent with various
percentage of mismatches............................................................................................94
Figure 6- 2 Confusion matrix of types of fault classified using proposed classification
method..........................................................................................................................99
Figure 6- 3 Interconnection from Network server to NodeRed and to different
applications via MQTT and HTPP protocols.............................................................101
Figure 6- 4 Gateway GUI .........................................................................................102
Figure 6- 5 Application Server receiving all the data from end node........................103
Figure 6- 6 Screenshot of message received in GoogleSheet....................................104
Figure 6- 7 Screenshot of received message in Ubidots using HTTP .......................106
Figure 6- 8 Comparison of CNN-based methods and proposed method in terms of
training time and number of parameters....................................................................108
Figure 6- 9 Core allocation in Opal-RT for real-time simulation..............................109
Figure 6- 10 Hardware setup for real-time simulation...............................................110
Figure 6- 11 Results of digital real-time simulation: (a) shorted string fault in real time,
(b) equivalent 2D image of shorted string fault...........................................................111



List of Tables
Table 2- 1 Protection Devices Standard [58]........................................................... 26
Table 4- 1 Comparison of LoRa to Different Networks Technologies commonly
used in Internet of Things Technology [79]............................................................. 67
Table 4- 2 Illustration of Spreading Factor at Uplink frequency 125kHz with
Payload of 11-bytes [79].......................................................................................... 74
Table 4- 3 Chracteristics of LoRa Modulation ........................................................ 76
Table 4- 4 Types of Activation in Commissioning [79] .......................................... 81
Table 5- 1 Testing Conditions for Studying PV Faults............................................ 85
Table 6- 1 Number of Faults Considered for Training and Testing......................... 94
Table 6- 2 Number of Faults Considered for Training and Testing......................... 94
Table 6- 3 Measured PV Array Power and Digital Object ...................................... 95
Table 6- 4 Parameter settings of trained ConvMixer............................................... 96
Table 6- 5 Performance of Classification Metrics by Proposed ConvMixer........... 97
Table 6- 6 Classification Matrix of Proposed ConvMixer for Testing Data............ 98
Table 6- 7 Classification Performance of Proposed Method and ML Methods .... 107
Table 6- 8 Comparison of CNN-based Methods.................................................... 107




[1]Word Nuclear News, “IEA calls for ‘comprehensive’ approach to Electricity Security,” IEA calls for “comprehensive” approach to electricity security : Energy & Environment - World Nuclear News, https://world-nuclear-news.org/Articles/IEA-calls-for-comprehensive-approach-to-electricit (accessed Jun. 1, 2023).
[2]NREL, Ed., “Renewable Electricity Futures Study,” NREL.gov, https://www.nrel.gov/analysis/re-futures.html (accessed Jun. 1, 2023).
[3]IRENA, Ed., “Solar energy,” IRENA, https://www.irena.org/Energy-Transition/Technology/Solar-energy (accessed Jun. 1, 2023).
[4]A. A. M. Sayigh, "PV Systems: Modeling, Design, and Fault Diagnosis," IEEE Transactions on Industrial Electronics, vol. 63, no. 2, pp. 898-908, 2016.
[5]S. K. Firth, K. J. Lomas, and S. J. Rees, “A simple model of PV system performance and its use in fault detection,” Solar Energy, vol. 84, no. 4, pp. 624–635, 2010.
[6]L. C. G. Silva, "The cost of photovoltaic electricity," Renewable and Sustainable Energy Reviews, vol. 14, pp. 547-557, 2010.
[7]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.
[8]D. S. Pillai, F. Blaabjerg, and N. Rajasekar, “A comparative evaluation of advanced fault detection approaches for PV systems,” IEEE Journal of Photovoltaics, vol. 9, no. 2, pp. 513–527, 2019.
[9]D. 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.
[10]A. Mellit and S. Kalogirou, “Artificial intelligence and internet of things to improve efficacy of diagnosis and remote sensing of solar photovoltaic systems: Challenges, recommendations and Future Directions,” Renewable and Sustainable Energy Reviews, vol. 143, p. 110889, 2021.
[11]S. Ali, "Line-to-line faults in photovoltaic systems," Journal of Clean Energy Technologies, vol. 2, no. 6, pp. 479-483, 2014.
[12]Y. B. Shao, "Shorted module detection in photovoltaic systems," IEEE Transactions on Industrial Electronics, vol. 59, no. 7, pp. 2788-2796, 2012.
[13]B. Bahrami, "Shorted string detection in photovoltaic systems," IEEE Transactions on Power Electronics, vol. 28, no.
[14]A. Eskandari, J. Milimonfared, and M. Aghaei, “Fault detection and classification for photovoltaic systems based on hierarchical classification and machine learning technique,” IEEE Trans. on Industrial Electronics, vol. 68, no. 12, pp. 12750–12759, 2021.
[15]Y.-Y. Hong and R. A. Pula, “Detection and classification of faults in photovoltaic arrays using a 3D convolutional neural network,” Energy, vol. 246, p. 123391, 2022.
[16]Y.-Y. Hong and R. A. Pula, “Diagnosis of PV faults using digital twin and convolutional mixer with Lora Notification System,” Energy Reports, vol. 9, pp. 1963–1976, 2023.
[17]Y.-Y. Hong and R. A. Pula, “Methods of photovoltaic fault detection and classification: A Review,” Energy Reports, vol. 8, pp. 5898–5929, 2022.
[18]W. Chine, A. Mellit, V. Lughi, A. Malek, G. Sulligoi, and A. Massi Pavan, “A novel fault diagnosis technique for photovoltaic systems based on artificial neural networks,” Renewable Energy, vol. 90, pp. 501–512, 2016.
[19]S. Fadhel, C. Delpha, D. Diallo, I. Bahri, A. Migan, M. Trabelsi, and M. F. Mimouni, “PV shading fault detection and classification based on I-V curve using principal component analysis: Application to isolated PV system,” Solar Energy, vol. 179, pp. 1–10, 2019.
[20]R. Hariharan, M. Chakkarapani, G. Saravana Ilango and C. Nagamani, "A method to detect photovoltaic array faults and partial shading in PV Systems," IEEE Journal of Photovoltaics, vol. 6, no. 5, pp. 1278 - 1285, 2016.
[21]J. Chen, "A review of thermal imaging-based fault detection for photovoltaic systems," Renewable and Sustainable Energy Reviews, vol. 81, pp. 687-699, 2017.
[22]X. Liu, "A review of fault diagnosis methods for photovoltaic systems," Renewable Energy, vol. 140, pp. 1189-1206, 2019.
[23]Z. Huang and L. Guo, “Research and implementation of microcomputer online fault detection of Solar Array,” 4th International Conference on Computer Science and Education, pp. 1052-1055, 2009.
[24]K. Jia, C. Gu, L. Li, Z. Xuan, T. Bi, and D. Thomas, “Sparse voltage amplitude measurement based fault location in large-scale photovoltaic power plants,” Applied Energy, vol. 211, pp. 568–581, 2018.
[25]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.
[26]S. Silvestre, A. Chouder, and E. Karatepe, “Automatic fault detection in Grid Connected PV systems,” Solar Energy, vol. 94, pp. 119–127, 2013.
[27]A. Eskandari, J. Milimonfared, and M. Aghaei, “Fault detection and classification for photovoltaic systems based on hierarchical classification and machine learning technique,” IEEE Trans. on Industrial Electronics, vol. 68, no. 12, pp. 12750–12759, 2021.
[28]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. on Industrial Electronics, vol. 64, no. 11, pp. 8546–8556, 2017.
[29]S. R. Madeti and S. N. Singh, “Modeling of PV system based on experimental data for fault detection using KNN method,” Solar Energy, vol. 173, pp. 139–151, 2018.
[30]R. Benkercha and S. Moulahoum, “Fault detection and diagnosis based on C4.5 decision tree algorithm for grid connected PV system,” Solar Energy, vol. 173, pp. 610–634, 2018.
[31]Z. Chen, F. Han, L. Wu, J. Yu, S. Cheng, P. Lin, and H. 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.
[32]Z. Chen, L. Wu, S. Cheng, P. Lin, Y. Wu, and W. Lin, “Intelligent fault diagnosis of photovoltaic arrays based on optimized kernel extreme learning machine and I-V characteristics,” Applied Energy, vol. 204, pp. 912–931, 2017.
[33]M. Dhimish, V. Holmes, B. Mehrdadi, M. Dales, and P. Mather, “Photovoltaic fault detection algorithm based on theoretical curves modelling and fuzzy classification system,” Energy, vol. 140, pp. 276–290, 2017.
[34]Chao, K.-H. et al. (2014) “An intelligent fault detection method of a photovoltaic module array using wireless sensor networks,” International Journal of Distributed Sensor Networks, 10(5), p. 540147. Available at:
[35]G. Liu and W. Yu, "A fault detection and diagnosis technique for solar system based on Elman neural network," 2017 IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), Chengdu, China, 2017, pp. 473-480.
[36]H. Zhu, L. Lu, J. Yao, S. Dai, and Y. Hu, “Fault diagnosis approach for photovoltaic arrays based on unsupervised sample clustering and probabilistic neural network model,” Solar Energy, vol. 176, pp. 395–405, 2018.
[37]E. Pedersen et al., "PV Array Fault Detection using Radial Basis Networks," 2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA), Patras, Greece, 2019, pp. 1-4,
[38]B. Basnet, H. Chun, and J. Bang, “An intelligent fault detection model for fault detection in Photovoltaic Systems,” Journal of Sensors, vol. 2020, pp. 1–11, 2020.
[39]X. Li, W. Li, Q. Yang, W. Yan and A. Y. Zomaya, "An unmanned inspection system for multiple defects detection in photovoltaic plants," IEEE Journal of Photovoltaics, vol. 10, no. 2, pp. 568-576, March 2020.
[40]A. Kirsten Vidal de Oliveira, M. Aghaei, and R. Rüther, “Aerial infrared thermography for low-cost and fast fault detection in utility-scale PV power plants,” Solar Energy, vol. 211, pp. 712–724, 2020.
[41]F. Aziz, A. Ul Haq, S. Ahmad, Y. Mahmoud, M. Jalal and U. Ali, "A novel convolutional neural network-based approach for fault classification in photovoltaic arrays," IEEE Access, vol. 8, pp. 41889-41904, 2020.
[42]P. Lin, Z. Qian, X. Lu, Y. Lin, Y. Lai, S. Cheng, Z. Chen, and L. Wu, “Compound fault diagnosis model for photovoltaic array using multi-scale Se-ResNet,” Sustainable Energy Technologies and Assessments, vol. 50, p. 101785, 2022.
[43]W. Tang, Q. Yang, K. Xiong, and W. Yan, “Deep learning based automatic defect identification of photovoltaic module using electroluminescence images,” Solar Energy, vol. 201, pp. 453–460, 2020.
[44]H. Li, X. Fu, and T. Huang, “Research on surface defect detection of solar PV panels based on Pre-Training Network and feature fusion,” IOP Conference Series: Earth and Environmental Science, vol. 651, no. 2, p. 022071, 2021.
[45]X. Lu, P. Lin, S. Cheng, G. Fang, X. He, Z. Chen and L. Wu, “Fault diagnosis model for photovoltaic array using a dual-channels convolutional neural network with a feature selection structure”, Energy Conversion and Management, vol. 248, p. 114777, 2021.
[46]S. Lu, T. Sirojan, B. T. Phung, D. Zhang and E. Ambikairajah, "DA-DCGAN: An effective methodology for DC series arc fault diagnosis in photovoltaic systems," IEEE Access, vol. 7, pp. 45831-45840, 2019.
[47]Y. Liu, K. Ding, J. Zhang, Y. Li, Z. Yang, W. Zheng, and X. Chen, “Fault diagnosis approach for photovoltaic array based on the stacked auto-encoder and clustering with I-V curves,” Energy Conversion and Management, vol. 245, p. 114603, 2021.
[48]Admin, “Different types of solar PV systems: On grid, hybrid & off grid solar,” Deege Solar, 26-May-2022. [Online]. Available: https://www.deegesolar.co.uk/different_types_of_solar_pv_systems/#:~:text=There%20are%20three%20main%20types,from%20their%20solar%20panel%20installation. [Accessed: 29-Jan-2023].
[49]L. Chaar, “Solar Power Conversion,” Power Electronics Handbook, pp. 661–672, 2007.
[50]N. Jenkins and J. Thornycroft, “Grid connection of Photovoltaic Systems,” McEvoy's Handbook of Photovoltaics, pp. 847–876, 2018.
[51]J. Green, M. Emery, Y. Hishikawa, W. Warta, and E. Dunlop, “Solar cell efficiency tables (version 49),” IEEE Journal of Photovoltaics, vol. 10, no. 6, pp. 1900–1909, 2020.
[52]X. H. Nguyen and M. P. Nguyen, “Mathematical Modeling of Photovoltaic Cell/module/arrays with tags in MATLAB/Simulink,” Environmental Systems Research, vol. 4, no. 1, 2015.
[53]J. C. Rosas-Caro, J. M. Ramirez, F. Z. Peng, and A. Valderrabano, “A DC–DC multilevel boost converter,” IET Power Electronics, vol. 3, no. 1, p. 129, 2010.
[54]S. Salman, X. AI, and Z. WU, “Design of a P-&-O algorithm based MPPT Charge Controller for a stand-alone 200W PV system,” Protection and Control of Modern Power Systems, vol. 3, no. 1, 2018.
[55]Office of Energy Efficiency & Renewable Energy, “Solar integration: Inverters and grid services basics,” Energy.gov, https://www.energy.gov/eere/solar/solar-integration-inverters-and-grid-services-basics (accessed Jun. 1, 2023).
[56]A. Emadi, "Power Electronics in Electric and Hybrid Electric Vehicles," in Power Electronics Handbook, Third Edition, M. H. Rashid, Ed. Academic Press, 2016, pp. 847-894.
[57]"IEEE Standard Terminology for Power and Distribution Transformers," in IEEE Std C57.12.80-2010 (Revision of IEEE Std C57.12.80-2002) , vol., no., pp.1-60, 17 Dec. 2010
[58]D. 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.
[59]A. Colli, “Failure mode and effect analysis for Photovoltaic Systems,” Renewable and Sustainable Energy Reviews, vol. 50, pp. 804–809, 2015.
[60]J. C. Hernandez and P. G. Vidal, “Guidelines for protection against electric shock in PV generators,” IEEE Transactions on Energy Conversion, vol. 24, no. 1, pp. 274–282, 2009.
[61]S. R. Madeti and S. N. Singh, “A comprehensive study on different types of faults and detection techniques for solar photovoltaic system,” Solar Energy, vol. 158, pp. 161–185, 2017.
[62]Y. C. Ko and W. T. Chen, “A review of potential-induced degradation in photovoltaic modules,” Renewable and Sustainable Energy Reviews, vol. 59, pp. 1170–1179, 2016.
[63]J. R. Sherif, S. M. M. Ibraheem, and M. F. A. Rasheed, “Investigation of light induced degradation in silicon photovoltaic cells,” in 2015 7th International Renewable and Sustainable Energy Conference (IRSEC), 2015, pp. 1–5.
[64]X. Zhang, L. Wang, and X. Liu, “Aging-related degradation of photovoltaic modules,” Energy Conversion and Management, vol. 195, pp. 507–515, 2019.
[65]B. E. A. Saleh, “Hot-spot degradation in photovoltaic modules,” Journal of Renewable and Sustainable Energy, vol. 4, no. 4, p. 043108, 2012.
[66]Z. Wang and T. Oates, “Imaging time-series to improve classification and imputation,” arXiv.org, 01-Jun-2015. [Online]. Available: https://arxiv.org/abs/1506.00327. [Accessed: 28-Mar-2022].
[67]"pyts.image.RecurrencePlot — pyts 0.12.0 documentation", Pyts.readthedocs.io, 2022. [Online]. Available: https://pyts.readthedocs.io/en/stable/generated/pyts.image.RecurrencePlot.html. [Accessed: 18- Sep- 2022].
[68]M. Grieves, Digital Twin: Manufacturing Excellence through virtual factory replication, https://www.researchgate.net/publication/275211047_Digital_Twin_Manufacturing_Excellence_through_Virtual_Factory_Replication (accessed May 31, 2023).
[69]E. J. Tuegel, A. R. Ingraffea, T. G. Eason, and S. M. Spottswood, “Reengineering aircraft structural life prediction using a digital twin,” International Journal of Aerospace Engineering, vol. 2011, pp. 1–14, 2011. doi:10.1155/2011/154798
[70]S. Paul, “Keras Documentation: Image classification with convmixer,” Keras. [Online]. Available: https://keras.io/examples/vision/convmixer/. [Accessed: 28-Mar-2022].
[71]V. Dumoulin and F. Visin, “A guide to convolution arithmetic for deep learning,” arXiv.org, 11-Jan-2018. [Online]. Available: https://arxiv.org/abs/1603.07285. [Accessed: 06-Apr-2023].
[72]C.-F. Wang, “A basic introduction to separable convolutions,” Medium, 14-Aug-2018. [Online]. Available: https://towardsdatascience.com/a-basic-introduction-to-separable-convolutions-b99ec3102728. [Accessed: 06-Apr-2023].
[73]A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, and N. Houlsby, “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv.org, 03-Jun-2021. [Online]. Available: https://arxiv.org/abs/2010.11929. [Accessed: 06-Apr-2023].
[74]N. Singh, “Paper explained- vision transformers (bye bye convolutions),” Medium, 13-Nov-2020. [Online]. Available: https://medium.com/analytics-vidhya/vision-transformers-bye-bye-convolutions-e929d022e4ab. [Accessed: 06-Apr-2023].
[75]S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” arXiv.org, 02-Mar-2015. [Online]. Available: https://arxiv.org/abs/1502.03167. [Accessed: 06-Apr-2023].
[76]M. Lin, Q. Chen, and S. Yan, “Network in Network,” arXiv.org, 04-Mar-2014. [Online]. Available: https://arxiv.org/abs/1312.4400. [Accessed: 06-Apr-2023].
[77]A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” arXiv.org, 06-Dec-2017. [Online]. Available: https://arxiv.org/abs/1706.03762. [Accessed: 06-Apr-2023].
[78]J. Devlin and M.-W. Chang, “Open sourcing Bert: State-of-the-art pre-training for Natural Language Processing,” – Google AI Blog. [Online]. Available: https://ai.googleblog.com/2018/11/open-sourcing-bert-state-of-art-pre.html. [Accessed: 06-Apr-2023].
[79]R. Wenner, “What are Lora and Lorawan?,” The Things Network, 12-Dec-2021. [Online]. Available: https://www.thethingsnetwork.org/docs/lorawan/what-is-lorawan/. [Accessed: 28-Mar-2022].
[80]R. S. Sinha, Y. Wei, and S.-H. Hwang, “A survey on LPWA technology: Lora and Nb-IOT,” ICT Express, vol. 3, no. 1, pp. 14–21, 2017.
[81]Semtech, “What are Lora® and Lorawan®?,” LoRa Developer Portal. [Online]. Available: https://lora-developers.semtech.com/documentation/tech-papers-and-guides/lora-and-lorawan/. [Accessed: 07-Apr-2023].
[82]3GLTEInfo, Ed., “Lora Architecture - Lorawan tutorial,” 3GLTEInfo, https://www.3glteinfo.com/lora/lora-architecture/ (accessed Jun. 1, 2023).

電子全文 電子全文(網際網路公開日期:20280613)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top