Three-state operation method and system for spraying of power transmission and distribution unmanned aerial vehicle

Through the improved Faster R-CNN model and convolutional neural network model combined with the drone robot arm, a three-state operation method for transmission lines and distribution lines is realized, and the single modal problem of the existing drone spraying system is solved, the spraying efficiency and safety are improved, and the spraying quality is ensured.

CN120431499AActive Publication Date: 2025-08-05STATE GRID JIANGXI ELECTRIC POWER CO LTD +1
9 Cites 0 Cited by

Patent Information

Application Number
CN202510936716.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-08
Publication Date
2025-08-05
Estimated Expiration
2045-07-08

AI Technical Summary

Technical Problem

The existing drone spraying system can only perform single mode spraying, and cannot be applied to both transmission lines and distribution lines. It lacks evaluation of the spraying effect, resulting in low efficiency and insufficient safety.

Method used

The improved Faster R-CNN model and convolutional neural network model are used to identify and evaluate the type of spraying equipment and combine the drone robot arm and spraying robot arm to realize the three-state operation method, including surface cleaning, autonomous spraying control and real-time quality evaluation.

Benefits of technology

Accurate spraying of transmission lines and distribution network lines is achieved, avoiding waste of paint, improving operational accuracy and safety, ensuring that the spraying quality meets requirements, and extending the service life of the equipment.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a three-state operation method and system for spraying of a power transmission and distribution unmanned aerial vehicle, and the method comprises the following steps: carrying out a spraying experiment on spraying equipment, obtaining a visible light image to construct a data set, constructing an improved Faster R-CNN model and a convolutional neural network model, and carrying out the three-state operation of the spraying of the power transmission and distribution unmanned aerial vehicle. Respectively inputting the data set and the visible light image into the constructed model for optimization, and respectively obtaining a spraying equipment type identification model and a spraying quality evaluation model; after the unmanned aerial vehicle carries the spraying mechanical arm to fly to a to-be-sprayed area, the spraying equipment type recognition model is adopted to recognize the type of to-be-sprayed equipment, recognized spraying equipment is obtained, spraying is conducted, the spraying mass fraction is obtained, the spraying mass fraction is detected through the spraying quality evaluation model, and when the spraying mass fraction does not meet a set threshold value, the spraying quality evaluation model judges that the spraying quality evaluation model does not meet the set threshold value. And spraying is continued until the spraying mass fraction reaches a threshold value. The spraying speed can be increased through self-adaptive adjustment of spraying flight control, and manual operation is reduced.
Need to check novelty before this filing date? Find Prior Art