Power Transmission Fault Detection Using Hyperparameter-Tuned YOLOv11 with XAI
Bibliographic record
Abstract
The secure and stable operation of power transmission lines is vital for maintaining uninterrupted electricity supply. Faults in these lines, caused by complex natural conditions or aging infrastructure, can lead to significant disruptions, highlighting the need for efficient fault detection. Existing methods face challenges such as complex backgrounds, multi-target scenarios, varying lighting conditions, and limited fault categories. This study addresses these limitations by introducing an improved fault detection framework based on YOLOv11, enhanced with hyperparameter optimization using a genetic algorithm. The incorporation of XAI provides interpretable model outcomes, offering actionable insights to support maintenance and monitoring tasks. Additionally, data augmentation techniques were employed to improve detection in underrepresented fault categories. Unlike previous approaches that focus on specific faults, such as insulator defects, this work identifies a wider range of fault scenarios. The proposed framework achieves an mAP@0.50 of 0.94 and an F1 score of 0.92 on the PTL-AI Furnas dataset, exceeding the benchmark result, demonstrating its effectiveness in addressing various fault detection challenges, and highlighting its potential for practical applications in maintenance and monitoring of power transmission lines.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".