Fault Precognition System for Remaining Useful Life Estimation in Bearing Systems Using Autoencoder-LSTM and Clustering Techniques
Bibliographic record
Abstract
This paper proposes a fault precognition system designed for predictive maintenance in bearing systems aimed at improving Remaining Useful Life (RUL) estimation accuracy.This study makes use of the Pronostia-bearing dataset, a recognized standard for RUL prediction and predictive maintenance.It includes vibration data captured by accelerometer sensors along two axes (X and Y), which shows how bearings deteriorate under different operation circumstances.The extensive size of the dataset, which includes several bearings experiencing progressive deterioration, guarantees strong validation of the suggested fault precognition and RUL prediction system in actual maintenance situations.The system utilizes the Pronostia bearing dataset, employing time-domain feature extraction, automated feature ranking, and fault pattern classification through Kmeans clustering with Silhouette Coefficients.A core component of the system is an Autoencoder-LSTM model, which identifies early fault occurrences by analyzing reconstruction loss thresholds-quantitative measures of deviation between observed and reconstructed data.These thresholds serve as indicators of anomalous behaviour, distinguishing normal operations from fault-prone data clusters.The system then estimates RUL using various LSTM variants, including Vanilla LSTM, BiLSTM, CNN-LSTM, StackLSTM, ConvLSTM and Encoder-Decoder LSTM, with performance evaluated using Mean Squared Error (MSE) and R² scores.The results demonstrate that incorporating fault precognition into the system significantly enhances prediction accuracy, facilitating proactive maintenance and improving operational reliability.
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 | 0.001 |
| 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".