| The distribution of power supply lines in Jiangsu Province is complicated,as most of the power transmission and transformation equipments of which are distributed in the Yangtze River Delta economic belt area with multiple waters and bridge structures.As industrial power supplies are increasingly demanding reliability of power supplies and the scale of ultra-high voltage grid is gradually expanding with overhead line being denser,it brings more work pressure to accident repair,operation inspection for the line inspection team.In view of the scattered distribution of overhead lines,it causes adverse effects for the repair and inspection of the lines,which brings severe challenges to the safe operation of the entire power grid.At present,line inspection work is mainly manual mode with a large workload and poor quality,and the inspection environment is getting worse and worse,which has caused great security risks to the staff.Due to the long inspection cycle and the limitation of the viewing angle and the long viewing distance,it is difficult to conduct a thorough and detailed inspection.For these missing hidden defects,it will increase the risk of emergency repair and is not conducive to line defect analysis.Based on the above research background,a patrol inspection technology based on distance intelligent image recognition for transmission lines is designed and studied in this paper.By picking up the monitoring image set near the line,the fault of wires and insulator strings are effectively identified.It is beneficial for the operation and maintenance personnel to grasp the operation status of the line in real time and improve the early warning capability for the fault.Especially for some blind spots that are unreachable and visually unobservable by staff,this technology can effectively solve the problem of remote monitoring of power transmission lines and reduce the difficulty of manual inspection by using UAV or image acquisition technology.The dissertetion is divided into the following four parts: The first part introduces the overall functional requirements of the line inspection system,and introduces some key technologies for long-distance transmission line inspection.The second part focuses on the image processing algorithm for on-site acquisition,namely themulti-string line information extraction algorithm based on the Ratio operator for edge detection and Hough transform analysis.The third part solves the problem of mutual occlusion between insulators by analyzing the effective extraction method of the entire insulator sub-key contour.Then the last part develops the application Jiangsu 500 kV transmission line remote control inspection platform with intelligent options and multiple workbench strategies.The system includes two parts: front-end camera equipment and background processing.The front-end equipment completes the image acquisition of the line,the tower and the surrounding environment,and the background processing mainly performs the functions of command release,real-time retrieval,event reporting and defect processing.It can improve the inspection accuracy and the corresponding speed of the accident through an effective image processing algorithm. |
PDF Full Text Request