Power Transformer Prognostics and Health Management Using Machine Learning: A Review and Future Directions
Bibliographic record
Abstract
Power transformers (PTs) play a vital role in the electrical power system. Assessing their health to predict their remaining useful life is essential to optimise maintenance. Scheduling the right maintenance for the right equipment at the right time is the ultimate goal of any power system utility. Optimal maintenance has a number of benefits: human and social, by limiting sudden service interruptions, and economic, due to the direct and indirect costs of unscheduled downtime. PT now produces large amounts of easily accessible data due to the increasing use of IoT, sensors, and connectivity between physical assets. As a result, power transformer prognostics and health management (PT-PHM) methods are increasingly moving towards artificial intelligence (AI) techniques, with several hundreds of scientific papers published on the topic of PT-PHM using AI techniques. On the other hand, the world of AI is undergoing a new evolution towards a third generation of AI models: large-scale foundation models. What is the current state of research in PT-PHM? What are the trends and challenges in AI and where do we need to go for power transformer prognostics and health management? This paper provides a comprehensive review of the state of the art in PT-PHM by analysing more than 200 papers, mostly published in scientific journals. Some elements to guide PT-PHM research are given at the end of the document.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".