Multi-Condition Remaining Useful Life Prediction Based on Mixture of Encoders
Accurate Remaining Useful Life (RUL) prediction is vital for effective prognostics in and the health management of industrial equipment, particularly under varying operational conditions. Existing approaches to multi-condition RUL prediction often treat each working condition independently, failing...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/27/1/79 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588592368582656 |
|---|---|
| author | Yang Liu Bihe Xu Yangli-ao Geng |
| author_facet | Yang Liu Bihe Xu Yangli-ao Geng |
| author_sort | Yang Liu |
| collection | DOAJ |
| description | Accurate Remaining Useful Life (RUL) prediction is vital for effective prognostics in and the health management of industrial equipment, particularly under varying operational conditions. Existing approaches to multi-condition RUL prediction often treat each working condition independently, failing to effectively exploit cross-condition knowledge. To address this limitation, this paper introduces MoEFormer, a novel framework that combines a Mixture of Encoders (MoE) with a Transformer-based architecture to achieve precise multi-condition RUL prediction. The core innovation lies in the MoE architecture, where each encoder is designed to specialize in feature extraction for a specific operational condition. These features are then dynamically integrated through a gated mixture module, enabling the model to effectively leverage cross-condition knowledge. A Transformer layer is subsequently employed to capture temporal dependencies within the input sequence, followed by a fully connected layer to produce the final prediction. Additionally, we provide a theoretical performance guarantee for MoEFormer by deriving a lower bound for its error rate. Extensive experiments on the widely used C-MAPSS dataset demonstrate that MoEFormer outperforms several state-of-the-art methods for multi-condition RUL prediction. |
| format | Article |
| id | doaj-art-ef7495633c3d4a4c934938c66c3cbbea |
| institution | Kabale University |
| issn | 1099-4300 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj-art-ef7495633c3d4a4c934938c66c3cbbea2025-01-24T13:31:55ZengMDPI AGEntropy1099-43002025-01-012717910.3390/e27010079Multi-Condition Remaining Useful Life Prediction Based on Mixture of EncodersYang Liu0Bihe Xu1Yangli-ao Geng2Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing 100044, ChinaKey Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing 100044, ChinaKey Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing 100044, ChinaAccurate Remaining Useful Life (RUL) prediction is vital for effective prognostics in and the health management of industrial equipment, particularly under varying operational conditions. Existing approaches to multi-condition RUL prediction often treat each working condition independently, failing to effectively exploit cross-condition knowledge. To address this limitation, this paper introduces MoEFormer, a novel framework that combines a Mixture of Encoders (MoE) with a Transformer-based architecture to achieve precise multi-condition RUL prediction. The core innovation lies in the MoE architecture, where each encoder is designed to specialize in feature extraction for a specific operational condition. These features are then dynamically integrated through a gated mixture module, enabling the model to effectively leverage cross-condition knowledge. A Transformer layer is subsequently employed to capture temporal dependencies within the input sequence, followed by a fully connected layer to produce the final prediction. Additionally, we provide a theoretical performance guarantee for MoEFormer by deriving a lower bound for its error rate. Extensive experiments on the widely used C-MAPSS dataset demonstrate that MoEFormer outperforms several state-of-the-art methods for multi-condition RUL prediction.https://www.mdpi.com/1099-4300/27/1/79RUL predictiondeep learningmixture of encoderstransformer |
| spellingShingle | Yang Liu Bihe Xu Yangli-ao Geng Multi-Condition Remaining Useful Life Prediction Based on Mixture of Encoders Entropy RUL prediction deep learning mixture of encoders transformer |
| title | Multi-Condition Remaining Useful Life Prediction Based on Mixture of Encoders |
| title_full | Multi-Condition Remaining Useful Life Prediction Based on Mixture of Encoders |
| title_fullStr | Multi-Condition Remaining Useful Life Prediction Based on Mixture of Encoders |
| title_full_unstemmed | Multi-Condition Remaining Useful Life Prediction Based on Mixture of Encoders |
| title_short | Multi-Condition Remaining Useful Life Prediction Based on Mixture of Encoders |
| title_sort | multi condition remaining useful life prediction based on mixture of encoders |
| topic | RUL prediction deep learning mixture of encoders transformer |
| url | https://www.mdpi.com/1099-4300/27/1/79 |
| work_keys_str_mv | AT yangliu multiconditionremainingusefullifepredictionbasedonmixtureofencoders AT bihexu multiconditionremainingusefullifepredictionbasedonmixtureofencoders AT yangliaogeng multiconditionremainingusefullifepredictionbasedonmixtureofencoders |