Image-based Novel Fault Detection with Deep Learning Classifiers using Hierarchical Labels
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909151300419584 |
|---|---|
| author | Sergin, Nurettin Huang, Jiayu Chang, Tzyy-Shuh Yan, Hao |
| author_facet | Sergin, Nurettin Huang, Jiayu Chang, Tzyy-Shuh Yan, Hao |
| contents | One important characteristic of modern fault classification systems is the ability to flag the system when faced with previously unseen fault types. This work considers the unknown fault detection capabilities of deep neural network-based fault classifiers. Specifically, we propose a methodology on how, when available, labels regarding the fault taxonomy can be used to increase unknown fault detection performance without sacrificing model performance. To achieve this, we propose to utilize soft label techniques to improve the state-of-the-art deep novel fault detection techniques during the training process and novel hierarchically consistent detection statistics for online novel fault detection. Finally, we demonstrated increased detection performance on novel fault detection in inspection images from the hot steel rolling process, with results well replicated across multiple scenarios and baseline detection methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_17891 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Image-based Novel Fault Detection with Deep Learning Classifiers using Hierarchical Labels Sergin, Nurettin Huang, Jiayu Chang, Tzyy-Shuh Yan, Hao Machine Learning Artificial Intelligence One important characteristic of modern fault classification systems is the ability to flag the system when faced with previously unseen fault types. This work considers the unknown fault detection capabilities of deep neural network-based fault classifiers. Specifically, we propose a methodology on how, when available, labels regarding the fault taxonomy can be used to increase unknown fault detection performance without sacrificing model performance. To achieve this, we propose to utilize soft label techniques to improve the state-of-the-art deep novel fault detection techniques during the training process and novel hierarchically consistent detection statistics for online novel fault detection. Finally, we demonstrated increased detection performance on novel fault detection in inspection images from the hot steel rolling process, with results well replicated across multiple scenarios and baseline detection methods. |
| title | Image-based Novel Fault Detection with Deep Learning Classifiers using Hierarchical Labels |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2403.17891 |