Line bolt defect identification method based on combination of Phash algorithm and deep learning

Abstract

The invention discloses a line bolt defect identification method based on the combination of a Phash algorithm and deep learning, and the method comprises the steps: S1, collecting a bolt image of a power transmission line, carrying out the frame selection of a bolt position, and carrying out the segmentation and extraction of the selected image, and taking the image as an initial sample set; S2, judging a bolt missing condition in the initial sample set; S3, performing sample size expansion on the pictures with the bolts not missing in the initial sample set, and obtaining an expanded sample set; S4, using the expanded sample set as training data to be imported into the Faster R-CNN network model for training; and S5, identifying the bolt defect condition in the to-be-detected image, and selecting the bolt position, the method solves the problems that the existing bolt defect detection method is low in accuracy and easy to be influenced by external light, realizes a more universal bolt defect detection technology, has higher accuracy and applicability, and is suitable for popularization and application. The method provided by the invention has higher accuracy and applicability, and the acquisition of the data to be detected is not limited by weather, position and equipment factors any more.

Description

technical field [0001] The invention relates to the technical field of transmission line defect detection, in particular to a line bolt defect identification method based on Phash algorithm combined with deep learning. Background technique [0002] Transmission lines are an important part of the national power system. They usually exist in various complex environments. After being affected by external environmental factors such as wind, sun, and sun, it is inevitable that there will be varying degrees of loss. In order to provide residents with a more stable power supply environment, Maintenance of the line is essential. Manual maintenance is not only costly, but also lacks guarantee for the safety of maintenance personnel. Some extreme geographical locations will also hinder manual maintenance of transmission lines, and the emergence of drones undoubtedly provides a simpler and safer way for line maintenance. method. [0003] Although UAVs have been widely used in the def...

AI Technical Summary

Problems solved by technology

This method aims to solve the problem that the defect detection method in the prior art is greatly affected by external influences, the scope of application is narrow, the detection accuracy is not high in the case of missing bolts, and the problem that the bolt model without template cannot be detected

Images