Corrosive Dibenzyl Disulfide Concentration Prediction in Transformer Oil Using Deep Neural Network
Bibliographic record
Abstract
Dibenzyl disulfide (DBDS) is the most prevalent corrosive sulfur in transformer oil. It reacts with the transformer windings to produce copper sulfide (Cu2S) and gets deposited on the insulating paper’s surface, leading to interturn faults within the transformer windings. Hence, this article proposes a deep neural network (DNN) to predict the DBDS content in transformer oil. The parameters like interfacial tension (IFT), breakdown voltage (BDV), water content (WC), oxygen, neutralization number (NN), color, furan content, and specific gravity (SG) were used as features to train and test the DNN model. The performance of the regression model was evaluated using mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (${R}^{{2}}{)}$. Moreover, extensive analysis is carried out by varying feature combinations and test-train ratios to obtain the best prediction model. The values of DBDS predicted by DNN were further used to determine the corrosive sulfur concentration in transformer oil. The proposed method is validated on real-life transformer data obtained from the online dataset and on data obtained from the local power utilities. A comparative study showed better efficacy of the proposed DNN model than other prediction models for accurate DBDS prediction.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 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".