Failure modeling in a gas turbine system: Combining classification with anomaly detection models for two data selection strategies
Bibliographic record
Abstract
In this work, the sensor data from a gas turbine system is analyzed with the objective of failure modeling and prediction. Several maintenance incidents were recorded by the sensor system in two separate vehicles. Two approaches to selecting training data were used in the analysis. The first followed a traditional method of randomly selecting a certain percentage of data points to include in training. The second data selection strategy was to select certain incidents to include in training, with the remaining incidents unseen for testing. Using classifier and anomaly detection techniques, models of the system using 76 predictor variables were trained to distinguish between healthy and failed system states in a two-class problem. Significant differences in performance results were noted depending on the selection of data included in training. A rule-based classifier model was then applied to leverage the predictions from both the classifier and anomaly detection models yielding promising results. The construction of an ensemble model was an effective way to mitigate the challenges presented in the training strategies, where a single individual model would not succeed in both scenarios. The simplification of the system into two states could be regarded as restrictive when the `healthiness' of a system is nuanced; however, despite this simplification, good performance and accurate predictions could still be achieved.
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 | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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".