Early Fault Detection on CMAPSS with Unsupervised LSTM Autoencoders
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914256975298560 |
|---|---|
| author | Sánchez, P. Reyes, K. Radu, B. Fernández, E. |
| author_facet | Sánchez, P. Reyes, K. Radu, B. Fernández, E. |
| contents | This paper introduces an unsupervised health-monitoring framework for turbofan engines that does not require run-to-failure labels. First, operating-condition effects in NASA CMAPSS sensor streams are removed via regression-based normalisation; then a Long Short-Term Memory (LSTM) autoencoder is trained only on the healthy portion of each trajectory. Persistent reconstruction error, estimated using an adaptive data-driven threshold, triggers real-time alerts without hand-tuned rules. Benchmark results show high recall and low false-alarm rates across multiple operating regimes, demonstrating that the method can be deployed quickly, scale to diverse fleets, and serve as a complementary early-warning layer to Remaining Useful Life models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_10269 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Early Fault Detection on CMAPSS with Unsupervised LSTM Autoencoders Sánchez, P. Reyes, K. Radu, B. Fernández, E. Machine Learning This paper introduces an unsupervised health-monitoring framework for turbofan engines that does not require run-to-failure labels. First, operating-condition effects in NASA CMAPSS sensor streams are removed via regression-based normalisation; then a Long Short-Term Memory (LSTM) autoencoder is trained only on the healthy portion of each trajectory. Persistent reconstruction error, estimated using an adaptive data-driven threshold, triggers real-time alerts without hand-tuned rules. Benchmark results show high recall and low false-alarm rates across multiple operating regimes, demonstrating that the method can be deployed quickly, scale to diverse fleets, and serve as a complementary early-warning layer to Remaining Useful Life models. |
| title | Early Fault Detection on CMAPSS with Unsupervised LSTM Autoencoders |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2601.10269 |