AI-Driven Fault Detection in Grid-Connected PV Systems Through Machine Learning Models
Bibliographic record
Abstract
The rapid integration of photovoltaic (PV) systems into modern power grids necessitates robust fault detection mechanisms to ensure reliability, efficiency, and safe operation. While previous studies have applied machine learning (ML) techniques for PV fault diagnosis, most focus on isolated components rather than system-wide analysis. This paper proposes a novel fault detection framework that combines both panel-level and system-level datasets with advanced ML and deep learning (DL) models. The pipeline includes data preprocessing, feature engineering, dimensionality reduction, and model optimization to achieve high accuracy in classifying multiple fault categories. Experimental results show that the Random Forest Classifier achieved 99% accuracy (std. dev. 0.0009), outperforming Decision Tree (97%), k-Nearest Neighbor (95%), and Support Vector Classifier (94%). Deep learning models, including Artificial Neural Networks (ANN) and Autoencoders, also delivered nearly 99% accuracy. The results demonstrate that hybrid datasets coupled with ML/DL pipelines enable scalable, real-time PV fault detection and monitoring, thereby minimizing downtime and enhancing grid reliability.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".