Automated deep learning system for power line inspection image analysis and processing: architecture and design issues

The continuous growth in the scale of unmanned aerial vehicle (UAV) applications in transmission line inspection has resulted in a corresponding increase in the demand for UAV inspection image processing. Owing to its excellent performance in computer vision, deep learning has been applied to UAV inspection image processing tasks such as power line identification and insulator defect detection. Despite their excellent performance, electric power UAV inspection image processing models based on deep learning face several problems such as a small application scope, the need for constant retraining and optimization, and high R&D monetary and time costs due to the black-box and scene data-driven characteristics of deep learning. In this study, an automated deep learning system for electric power UAV inspection image analysis and processing is proposed as a solution to the aforementioned problems. This system design is based on the three critical design principles of generalizability, extensibility, and automation. Pre-trained models, fine-tuning (downstream task adaptation), and automated machine learning, which are closely related to these design principles, are reviewed. In addition, an automated deep learning system architecture for electric power UAV inspection image analysis and processing is presented. A prototype system was constructed and experiments were conducted on the two electric power UAV inspection image analysis and processing tasks of insulator self-detonation and bird nest recognition. The models constructed using the prototype system achieved 91.36% and 86.13% mAP for insulator self-detonation and bird nest recognition, respectively. This demonstrates that the system design concept is reasonable and the system architecture feasible .

Prototype Monitoring System for Power Line Inspection by Means of a PandaBoard

The national energy supplier （Eskom in South Africa） supplies electricity through thousands-of-kilometers of overhead power lines. The current methods of inspection of these overhead power lines are infrequent and expensive. In this paper, the authors present the development of a prototype monitoring system for power line inspection in South Africa. The developed prototype monitoring system collects data （information） from the overhead power lines, is remotely accessible and fits into a power line robot. The prototype monitoring system makes use ofa PandaBoard （SBC） with GPS receiver and 5 MP camera to collect data. Hardware fatigue is the biggest problem faced on the overhead power lines and is captured by means of the 5 MP camera and is displayed on a website hosted by the PandaBoard via Wi-Fi. The monitoring system has low power consumption, is light weight, compact and easily collects data. The data obtained from the prototype monitoring system was satisfactory and provides an improved solution for monitoring power lines for Eskom in South Africa.