A Fault Detection Method for Power Transmission Lines Using Aerial Images
Bibliographic record
Abstract
It is necessary to regularly detect faults to maintain the safety and stability of power lines. Insulators are one of the important electrical components in high-voltage transmission lines. It is extremely necessary to check the working status of insulators regularly. Traditional manual inspection is inefficient because it requires a significant amount of labor costs. In this paper, a method for detecting insulators' missing defect based on aerial images is proposed to address the issue by unmanned aerial vehicle (UAV). Firstly, the improved Faster R-CNN (region-based convolutional neural network) is used to identify and locate insulators in aerial images. Secondly, the U-Net image segmentation network segments insulators from the images. The adaptive threshold segmentation method completely separates the insulator from the background. Then the binary image of the insulator is obtained. Finally, the binary image is converted into a fault curve which is used for determining the missing insulators based on the distribution of the fault curve. By using collected insulator datasets on a 330kV overhead transmission line using a DJI M300 UAV platform and an onboard H20T camera/sensor, the detection accuracy of glass insulators is as high as 0.98 with the proposed algorithm. The positioning accuracy of the proposed algorithm is also higher than other algorithms. This method has high detection accuracy for missing defects in insulators. The experimental results show that compared with similar algorithms, this method has higher accuracy and efficiency.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".