A hybrid intelligent busbar protection strategy using hyperbolic S‐transforms and extreme learning machines
Bibliographic record
Abstract
Abstract In power systems, busbars connect important components such as generators, transmission lines, and loads. A typical fault occurrence on the busbar may result in the isolation of faulty sections from other normally operating parts of the system resulting from differential protection operation. Although the main busbars' protection scheme is differential protection, its operation is significantly affected by magnetic saturation of the current transformer (CT), particularly during external fault occurrence or energizing power transformers. Saturation of the CT may generate a spurious differential current and is the main reason for the differential scheme malfunctioning. Previous research presented different methods to modify and improve busbars' differential protection scheme. However, there has been lack of a comprehensive study to assess the efficiency of the busbar protection scheme regarding all involved, and influencing aspects including various fault types, energizing power transformer, (high) fault resistance, fault angle (changing from 0° to 360°), and the angle of the sources. Thus, in this study, a hybrid intelligent busbar protection scheme is proposed and the effects of all these factors are investigated. The proposed strategy utilizes the hyperbolic S‐transform as a signal processing technique to extract an efficient feature that is able to discriminate internal faults from other abnormal modes, that is, external faults and inrush current under CT saturation. To obtain this goal, a learning‐based classification method known as extreme learning machines is used to classify the system conditions based on the selected features. The proposed protection scheme was found to have low sensitivity to CT saturation and noise and was able to accurately detect internal faults from half a cycle to one cycle of the power system depending on the fault resistance.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| 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".