A Cost-Sensitive Transformer Model for Prognostics Under Highly Imbalanced Industrial Data
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909105231233024 |
|---|---|
| author | Beikmohammadi, Ali Hamian, Mohammad Hosein Khoeyniha, Neda Lindgren, Tony Steinert, Olof Magnússon, Sindri |
| author_facet | Beikmohammadi, Ali Hamian, Mohammad Hosein Khoeyniha, Neda Lindgren, Tony Steinert, Olof Magnússon, Sindri |
| contents | The rapid influx of data-driven models into the industrial sector has been facilitated by the proliferation of sensor technology, enabling the collection of vast quantities of data. However, leveraging these models for failure detection and prognosis poses significant challenges, including issues like missing values and class imbalances. Moreover, the cost sensitivity associated with industrial operations further complicates the application of conventional models in this context. This paper introduces a novel cost-sensitive transformer model developed as part of a systematic workflow, which also integrates a hybrid resampler and a regression-based imputer. After subjecting our approach to rigorous testing using the APS failure dataset from Scania trucks and the SECOM dataset, we observed a substantial enhancement in performance compared to state-of-the-art methods. Moreover, we conduct an ablation study to analyze the contributions of different components in our proposed method. Our findings highlight the potential of our method in addressing the unique challenges of failure prediction in industrial settings, thereby contributing to enhanced reliability and efficiency in industrial operations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_08611 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Cost-Sensitive Transformer Model for Prognostics Under Highly Imbalanced Industrial Data Beikmohammadi, Ali Hamian, Mohammad Hosein Khoeyniha, Neda Lindgren, Tony Steinert, Olof Magnússon, Sindri Machine Learning Artificial Intelligence The rapid influx of data-driven models into the industrial sector has been facilitated by the proliferation of sensor technology, enabling the collection of vast quantities of data. However, leveraging these models for failure detection and prognosis poses significant challenges, including issues like missing values and class imbalances. Moreover, the cost sensitivity associated with industrial operations further complicates the application of conventional models in this context. This paper introduces a novel cost-sensitive transformer model developed as part of a systematic workflow, which also integrates a hybrid resampler and a regression-based imputer. After subjecting our approach to rigorous testing using the APS failure dataset from Scania trucks and the SECOM dataset, we observed a substantial enhancement in performance compared to state-of-the-art methods. Moreover, we conduct an ablation study to analyze the contributions of different components in our proposed method. Our findings highlight the potential of our method in addressing the unique challenges of failure prediction in industrial settings, thereby contributing to enhanced reliability and efficiency in industrial operations. |
| title | A Cost-Sensitive Transformer Model for Prognostics Under Highly Imbalanced Industrial Data |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2402.08611 |