Pantograph arcing detection method and system, electronic equipment and storage medium
Through the combination of the object detection algorithm and the convolutional neural network VGG16, the problem of low accuracy of pantograph arc detection is solved, the precise detection and parameter acquisition of arcs are realized, the detection accuracy is improved, and the safe operation of rail trains is guaranteed.
CN115049583BActive Publication Date: 2025-03-25SHANGHAI ELECTRICGROUP CORP
2 Cites 0 Cited by
Patent Information
- Application Number
- CN202210370124.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-08
- Publication Date
- 2025-03-25
- Estimated Expiration
- 2042-04-08
AI Technical Summary
Technical Problem
In the prior art, the pantograph arc detection accuracy is not high, and there are problems such as background interference, binarization threshold selection deviation and processing area changes, resulting in missed detection and missed detection.
Method used
The object detection algorithm is used to process the image to be detected, the target area is determined, and boundary processing and arc detection are performed through the convolutional neural network VGG16 to determine whether arcs exist.
Benefits of technology
Accurate detection of arcs is achieved, the problems of background interference, threshold selection deviation and processing area changes are solved, detection accuracy is improved, and the safe operation of rail trains is guaranteed.
✦ Generated by Eureka AI based on patent content.
Abstract
The present invention discloses a pantograph arc detection method and system, electronic device and storage medium. The detection method includes processing an image to be detected based on a target detection algorithm to determine a target area; performing boundary processing on the target area according to the pantograph components; and detecting the target area after boundary processing based on a convolutional neural network VGG16 to determine whether an arc is burning. Aiming at the defect that the current traditional image processing technology has insufficient accuracy in pantograph arc detection, the present invention adopts a target detection algorithm, a boundary processing algorithm and a convolutional neural network VGG16 to determine whether an arc is burning, and realizes the pantograph arc area capture, arc classification and arc parameter acquisition based on a deep learning algorithm, solves the problems existing in the prior art such as the difficulty in determining the arc area, the deviation in the selection of the binarization threshold and the interference of the background noise in the graphics processing, realizes the accurate detection of arc, provides a strong guarantee for the safe operation of rail trains, and has the significance of industry promotion.
Need to check novelty before this filing date? Find Prior Art