Edge-Computing-Enabled Unmanned Module Defect Detection and Diagnosis System for Large-Scale Photovoltaic Plants

The power efficiency of photovoltaic (PV) modules is highly correlated with their health status. Under dynamically changing environments, PV defects could spontaneously form and develop into fatal faults during the daily operation of PV power plants. To facilitate defect detection with less human intervention, a nondestructive, contactless, and automatical visual inspection system with the help of unmanned aerial vehicles and edge computing is proposed in this article. During the processing of the incoming data stream, the system may collect some new, unknown, and unlabeled defects that have not been identified yet in the existing database. To distinguish them from the existing ones, a deep embedded restricted cluster algorithm is designed to identify the unknown and unlabeled PV module defects in an unsupervised manner. Limited by the resources of edge devices and the availability of images of PV defects for training, we developed an online solution combined with deep learning, data argumentation, and transfer learning to properly address the issues of running resource-hungry applications on edge devices and lack of training samples faced by the deep learning approaches used in the field. In addition, pointwise convolution layers are introduced into the network to reduce the parameters and the size of the model. With the reduction of the network depth of the deep convolutional neural network model and the features transferred from the learned defects, the resource consumption of our proposed approach is significantly reduced, and thus can be used on a wide range of edge devices to complete defect detection in a timely manner with high accuracy. The experimental results clearly demonstrate the practicality and effectiveness.

[1]  Tao Zhang,et al.  Fog and IoT: An Overview of Research Opportunities , 2016, IEEE Internet of Things Journal.

[2]  D. H. Kim,et al.  Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks. , 2017, Clinical radiology.

[3]  Martin K. Patel,et al.  GIS-based assessment of photovoltaic (PV) and concentrated solar power (CSP) generation potential in West Africa , 2018 .

[4]  Paulo F. Pires,et al.  On Enabling Sustainable Edge Computing with Renewable Energy Resources , 2018, IEEE Communications Magazine.

[5]  Qiang Yang,et al.  Transfer Learning based Photovoltaic Module Defect Diagnosis using Aerial Images , 2018, 2018 International Conference on Power System Technology (POWERCON).

[6]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Ravi Kiran Sarvadevabhatla,et al.  A Taxonomy of Deep Convolutional Neural Nets for Computer Vision , 2016, Front. Robot. AI.

[8]  Qiang Yang,et al.  IET Renewable Power Generation Special Issue: Performance Assessment and Condition Monitoring of Photovoltaic Systems for Improved Energy Yield Visible defects detection based on UAV-based inspection in large-scale photovoltaic systems , 2020 .

[9]  Abhishek Das,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[10]  Santiago Silvestre.  Strategies for Fault Detection and Diagnosis of PV Systems , 2018 .

[11]  Christian Riess,et al.  Automatic Classification of Defective Photovoltaic Module Cells in Electroluminescence Images , 2018, Solar Energy.

[12]  Fei Jiang,et al.  Big data issues in smart grid – A review , 2017 .

[13]  Mohd Abdullah,et al.  Micro-crack detection of multicrystalline solar cells featuring an improved anisotropic diffusion filter and image segmentation technique , 2014, EURASIP Journal on Image and Video Processing.

[14]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[15]  Jing Dong,et al.  Learning and transferring representations for image steganalysis using convolutional neural network , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[16]  Quoc V. Le,et al.  Domain Adaptive Transfer Learning with Specialist Models , 2018, ArXiv.

[17]  Paul Gill,et al.  Electrical Power Equipment Maintenance and Testing , 1997 .

[18]  Yincheng Qi,et al.  Multi-patch deep features for power line insulator status classification from aerial images , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[19]  Joseph Kuitche,et al.  Defect and safety inspection of 6 PV technologies from 56,000 modules representing 257,000 modules in 4 climatic regions of the United States , 2016, 2016 IEEE 43rd Photovoltaic Specialists Conference (PVSC).

[20]  Yi Pan,et al.  Edge Computing for the Internet of Things , 2018, IEEE Netw..

[21]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[22]  Chunhua Shen,et al.  Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition , 2017 .

[23]  Qiang Yang,et al.  Deep Learning Based Module Defect Analysis for Large-Scale Photovoltaic Farms , 2019, IEEE Transactions on Energy Conversion.

[24]  Xinbo Gao,et al.  Objective Video Quality Assessment Combining Transfer Learning With CNN , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[25]  E. Kaplani.  Degradation in Field-aged Crystalline Silicon Photovoltaic Modules and Diagnosis using Electroluminescence Imaging , 2016 .

[26]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Yuliya Voronko,et al.  Outdoor detection and visualization of hailstorm damages of photovoltaic plants , 2018 .

[28]  Jordan J. Bird,et al.  A Study on CNN Transfer Learning for Image Classification , 2018, UKCI.

[29]  Mahadev Satyanarayanan,et al.  The Emergence of Edge Computing , 2017, Computer.

[30]  Ying Sun,et al.  Reliable fault detection and diagnosis of photovoltaic systems based on statistical monitoring approaches , 2018 .

[31]  Mohsen Guizani,et al.  Deep Learning for IoT Big Data and Streaming Analytics: A Survey , 2017, IEEE Communications Surveys & Tutorials.

[32]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[33]  Ivan Laptev,et al.  Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[34]  Shivkumar Kalyanaraman,et al.  DeepSolarEye: Power Loss Prediction and Weakly Supervised Soiling Localization via Fully Convolutional Networks for Solar Panels , 2017, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[35]  Djemel Ziou,et al.  Is there a relationship between peak-signal-to-noise ratio and structural similarity index measure? , 2013, IET Image Process..

[36]  Roberto Pierdicca,et al.  DEEP CONVOLUTIONAL NEURAL NETWORK FOR AUTOMATIC DETECTION OF DAMAGED PHOTOVOLTAIC CELLS , 2018, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences.