Development of an Automatic Recognition Model for Phase Resolved Partial Discharge Patterns in Hydro-Generators
Bibliographic record
Abstract
Whether in the industrial, medical or real-world domains, more and more data is being collected. The common particularity of all these application domains is that a great part of this data is mostly unlabeled. So, learning useful representations with minimal expert supervision is a major challenge in artificial intelligence in the coming years. Recently, there has been a particular interest in unsupervised learning methods based on the idea of autoencoding. The purpose of these methods is to learn a mapping representation from a high-dimensional to a lower-dimensional representation space from which the original observations can be reconstructed. The variational form of these autoencoders, called the Variational AutoEncoders (VAEs), is particularly successful in almost all application areas. This enthusiasm comes from the fact that VAEs allow to take advantage of the theoretical foundations of the Variational Bayesian methods and the learning capabilities of artificial neural networks. In this paper, a model based on the use of VAEs is proposed for the development of an automatic recognition and unsupervised feature extraction of Phase Resolved Partial Discharge (PRPD) results measured from hydro-generators. The first step of this model is the pre-processing phase where external noise were removed. The second step is the learning phase which is based on two concatenated VAEs. Preliminary results indicate that the two-dimensional (2D) reduced latent space configuration encodes the difference in the intensity of the PRPD patterns as well as in the phase shift. More improvement is needed to extract features related to the shape of the PRPD patterns.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".