Real-Time Fault Diagnosis: A Transformer-Based Approach
Bibliographic record
Abstract
Fault diagnosis in process control and monitoring is crucial for ensuring safety and maintaining operational efficiency. Faults represent deviations from the normal trajectory of the system, indicating potential issues that require timely intervention. However, current fault diagnosis methods often encounter delays or low accuracy with many hyper parameters to tune, limiting their applicability and generalizability in real-world industrial settings, particularly in high-frequency data environments. To address these challenges, this paper proposes an online fault diagnosis strategy based on a modified transformer architecture, which is specifically tailored for time-series classification. By considering fault diagnosis as a classification problem, the proposed model provides real-time fault diagnosis in a highly parallelizable manner without introducing any systematic delays, which is crucial for maintaining seamless operation. This approach also mitigates real-world challenges such as missing data, asynchronous data flow, and delays. Leveraging deep-learning techniques, the proposed approach harnesses the in-herent parallelizability of attention-based models to enable rapid fault diagnosis without compromising accuracy. Furthermore, to increase the classification accuracy, a two-step training procedure is employed. To demonstrate the effectiveness of the proposed method, it is compared with other well-established fault diagnosis methods using the extended Tennessee Eastman Process Dataset. This research highlights the power of deep learning in enhancing fault diagnosis capabilities, paving the way for safer and more efficient industrial operations.
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 | 0.002 |
| 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 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".