Transformer-Based Bearing Fault Detection using Temporal Decomposition Attention Mechanism
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929632504184832 |
|---|---|
| author | Mirzaeibonehkhater, Marzieh Labbaf-Khaniki, Mohammad Ali Manthouri, Mohammad |
| author_facet | Mirzaeibonehkhater, Marzieh Labbaf-Khaniki, Mohammad Ali Manthouri, Mohammad |
| contents | Bearing fault detection is a critical task in predictive maintenance, where accurate and timely fault identification can prevent costly downtime and equipment damage. Traditional attention mechanisms in Transformer neural networks often struggle to capture the complex temporal patterns in bearing vibration data, leading to suboptimal performance. To address this limitation, we propose a novel attention mechanism, Temporal Decomposition Attention (TDA), which combines temporal bias encoding with seasonal-trend decomposition to capture both long-term dependencies and periodic fluctuations in time series data. Additionally, we incorporate the Hull Exponential Moving Average (HEMA) for feature extraction, enabling the model to effectively capture meaningful characteristics from the data while reducing noise. Our approach integrates TDA into the Transformer architecture, allowing the model to focus separately on the trend and seasonal components of the data. Experimental results on the Case Western Reserve University (CWRU) bearing fault detection dataset demonstrate that our approach outperforms traditional attention mechanisms and achieves state-of-the-art performance in terms of accuracy and interpretability. The HEMA-Transformer-TDA model achieves an accuracy of 98.1%, with exceptional precision, recall, and F1-scores, demonstrating its effectiveness in bearing fault detection and its potential for application in other time series tasks with seasonal patterns or trends. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_11245 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Transformer-Based Bearing Fault Detection using Temporal Decomposition Attention Mechanism Mirzaeibonehkhater, Marzieh Labbaf-Khaniki, Mohammad Ali Manthouri, Mohammad Machine Learning Artificial Intelligence Signal Processing Bearing fault detection is a critical task in predictive maintenance, where accurate and timely fault identification can prevent costly downtime and equipment damage. Traditional attention mechanisms in Transformer neural networks often struggle to capture the complex temporal patterns in bearing vibration data, leading to suboptimal performance. To address this limitation, we propose a novel attention mechanism, Temporal Decomposition Attention (TDA), which combines temporal bias encoding with seasonal-trend decomposition to capture both long-term dependencies and periodic fluctuations in time series data. Additionally, we incorporate the Hull Exponential Moving Average (HEMA) for feature extraction, enabling the model to effectively capture meaningful characteristics from the data while reducing noise. Our approach integrates TDA into the Transformer architecture, allowing the model to focus separately on the trend and seasonal components of the data. Experimental results on the Case Western Reserve University (CWRU) bearing fault detection dataset demonstrate that our approach outperforms traditional attention mechanisms and achieves state-of-the-art performance in terms of accuracy and interpretability. The HEMA-Transformer-TDA model achieves an accuracy of 98.1%, with exceptional precision, recall, and F1-scores, demonstrating its effectiveness in bearing fault detection and its potential for application in other time series tasks with seasonal patterns or trends. |
| title | Transformer-Based Bearing Fault Detection using Temporal Decomposition Attention Mechanism |
| topic | Machine Learning Artificial Intelligence Signal Processing |
| url | https://arxiv.org/abs/2412.11245 |