Sleeve fault diagnosis method and system
Through preprocessing and segmentation technology of infrared images, combined with grayscale-temperature matrix analysis, the problem of low efficiency of bushing fault diagnosis in the existing technology is solved, and efficient identification and positioning of transformer bushing faults is achieved, supporting complex backgrounds. Failure analysis below.
CN111179213AInactive Publication Date: 2020-05-19STATE GRID JIANGSU ELECTRIC POWER CO LTD RESEARCH INSTITUTE +4
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- STATE GRID JIANGSU ELECTRIC POWER CO LTD RESEARCH INSTITUTE
- Filing Date
- 2019-11-28
- Publication Date
- 2020-05-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
⚠Technical Problem
It is difficult for existing technologies to effectively identify and diagnose transformer bushing faults in complex backgrounds. In particular, relying on manual infrared image analysis is inefficient and cannot meet the needs of massive image analysis.
⚗Method used
By preprocessing the collected infrared images, including K-means clustering and noise removal, the SLIC and OTSU algorithms are used to segment the image, extract a single casing image, and determine the faulty casing and fault type through the grayscale-temperature matrix.
🎯Benefits of technology
It realizes the identification and location of single casing faults in complex infrared images, improves diagnosis efficiency, reduces dependence on technicians, and supports horizontal and vertical statistical analysis.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention discloses a sleeve fault diagnosis method and system. The method comprises the following steps: preprocessing an acquired sleeve infrared image to filter out a non-heating part; segmenting the image of which the non-heating part is filtered out to obtain a single sleeve image; diagnosing the sleeve fault according to the segmented single sleeve image. According to the invention, theinfrared image of the transformer sleeve is preprocessed and segmented, therefore, an infrared image of a single sleeve is obtained; the temperature of each part of the sleeve can be conveniently obtained by converting the gray scale of each pixel in the gray scale map of the infrared image of the single sleeve into the corresponding temperature value, the method is simple but very ingenious, thefaulted sleeve and the faulted area can be quickly positioned, the specific fault type can be judged, and convenience and quickness are achieved.
Need to check novelty before this filing date? Find Prior Art