Power transmission line defect detection method and device

Abstract

The invention relates to the technical field of power transmission line monitoring and operation and maintenance protection, and particularly provides a power transmission line defect detection method and device, and the method comprises the steps: obtaining an image of a power transmission line, and carrying out the preprocessing of the image of the power transmission line; performing state recognition on the power transmission line based on the preprocessed image of the power transmission line and a pre-constructed power transmission line defect detection model; wherein the pre-constructed power transmission line defect detection model is obtained by training a preprocessed image of the power transmission line with a manually annotated lead state. According to the technical scheme provided by the invention, automatic classification and identification of line defects can be realized, 24-hour real-time monitoring can be carried out on the line state, and the operation and maintenance intelligence level of the line is improved.

Description

Technical field [0001] The present invention relates to the field of transmission line monitoring and operation and maintenance protection technology, specifically to a transmission line defect detection method and apparatus. Background [0002] Transmission lines have a large number of transmission lines, a wide distribution range, usually in hilly, alpine and undesirable geological areas and other sparsely populated areas, and the operating conditions are extremely harsh. Affected by external environmental factors such as wind, icing, temperature for a long time, transmission lines may produce defects or damage, although such hidden dangers will not affect the equipment in a short period of time, but if they cannot be found and treated in time, it will not only increase the loss of the equipment and reduce the efficiency, but also cause major accidents such as wire breakage, substation equipment damage, distribution network shutdown, etc., directly threatening the safety of th...

AI Technical Summary

Problems solved by technology

This method relies heavily on the operating experience of background personnel, and the manpower consumption is huge and the efficiency is very low

Moreover, at present, image access is manually operated by inspectors. Taking drones as an example, the captured images are first stored locally on the drone, and then manually imported to the server after returning to the office. The timeliness is low and there is a lack of automatic defect detection technology.

Images