Primary power distribution system porcelain insulator detection method based on unmanned aerial vehicle autonomous vision

Abstract

The invention relates to a primary power distribution system porcelain insulator detection method based on autonomous vision of an unmanned aerial vehicle. The method comprises the following steps: 1) collecting original images of normal and faulty porcelain insulators; 2) preprocessing the original image, including original image augmentation, blurred image reconstruction and weak light image enhancement, performing quality evaluation on the preprocessed image, removing the image which does not meet the quality requirement, and marking to form a training data set; and 3) constructing a porcelain insulator fault detection model, performing training by adopting a two-step fine tuning mode according to the training data set, and performing porcelain insulator fault detection according to the trained porcelain insulator fault detection model. Compared with the prior art, the method has the advantages of high detection precision, high automation degree and the like.

Description

technical field [0001] The invention relates to the field of detection of porcelain insulators in a primary power distribution system, in particular to a method for detecting porcelain insulators in a primary power distribution system based on the autonomous vision of an unmanned aerial vehicle. Background technique [0002] The main distribution system consists of the power lines that carry electricity from substations to utility feeders. Inspection and maintenance of power system insulator damage and fractures are critical to continued power supply and public safety. Therefore, regular inspections of power line insulation and other components must be ensured beforehand in order to identify any faults and defects in advance. [0003] Insulator strings are an important piece of equipment in primary overhead distribution lines as they function as insulation and provide mechanical strength. The efficiency of insulators can be compromised when exposed to pollution, environmen...

AI Technical Summary

Problems solved by technology

Canopies or petticoats are made of ceramic, a non-porous waterproof material found on pin and disc insulators, providing a long leak path to avoid flashovers and perforations, which can result from cracked canopies The risk of network and power outage needs to be detected in advance to prevent future abnormalities. However, the current inspection of insulators on overhead distribution lines mostly stays in the manual inspection stage, which is time-consuming, laborious and inefficient.

Images