Semi-automatic fault database establishment method for power transmission and transformation line equipment
A power transmission and transformation line, semi-automatic technology, applied in the field of power system and computer vision, can solve problems such as time-consuming and labor-intensive, wasting manpower, delaying work progress, etc., to reduce the time to find faults, reduce safety hazards, reduce The effect of workload
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0033] (1) Data collection: first use the data collection device to collect relevant data of power transmission and transformation line equipment, and screen the data to establish an unclassified database. The data collection device uses a UAV to load a high-definition camera or a telephoto lens SLR, During data collection, in the mode of data flow, obtain pictures and videos of power transmission and transformation line equipment and equipment faults in batches;
[0034] (2) Data analysis: analyze and obtain the characteristic information of the target component, select some data with obvious characteristic information and high picture quality, and carry out labeling work on the target component. The pixels are greater than 6 million, and the picture has no ghosting and no occlusion;
[0035] (3) Data classification: Based on the principle of deep learning target detection, the marked data set is randomly divided into a training set and a test set in a ratio of 7:3 for model ...
Embodiment 2
[0041] (1) Data collection: first use the data collection device to collect relevant data of power transmission and transformation line equipment, and screen the data to establish an unclassified database. The data collection device uses a UAV to load a high-definition camera or a telephoto lens SLR, During data collection, in the mode of data flow, obtain pictures and videos of power transmission and transformation line equipment and equipment faults in batches;
[0042](2) Data analysis: analyze and obtain the characteristic information of the target component, select some data with obvious characteristic information and high picture quality, and carry out labeling work on the target component. The pixels are greater than 6 million, and the picture has no ghosting and no occlusion;
[0043] (3) Data classification: Based on the principle of deep learning target detection, the marked data set is randomly divided into a training set and a test set in a ratio of 8:2 for model t...
Embodiment 3
[0049] (1) Data collection: first use the data collection device to collect relevant data of power transmission and transformation line equipment, and screen the data to establish an unclassified database. The data collection device uses a UAV to load a high-definition camera or a telephoto lens SLR, During data collection, in the mode of data flow, obtain pictures and videos of power transmission and transformation line equipment and equipment faults in batches;
[0050] (2) Data analysis: analyze and obtain the characteristic information of the target component, select some data with obvious characteristic information and high picture quality, and carry out labeling work on the target component. The pixels are greater than 6 million, and the picture has no ghosting and no occlusion;
[0051] (3) Data classification: Based on the principle of deep learning target detection, the marked data set is randomly divided into training set and test set according to the ratio of 9:1, a...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com