An improved supervised contrastive learning with denoising diffusion probabilistic model for fault detection in industrial processes
Li, Daye, Dong, Jie, Peng, Kaixiang and Zhang, Qichun (2024) An improved supervised contrastive learning with denoising diffusion probabilistic model for fault detection in industrial processes. Process Safety and Environmental Protection. ISSN 09575820
Full text not available from this repository. (Request a copy)Abstract
The distribution of actual industrial process data is complex, and variations in data distribution caused by equipment wear and changing operating conditions can easily lead to model mismatch, presenting a severe challenge to fault diagnosis methods that assume data follows a Gaussian distribution. In this context, we propose a novel fault detection method based on generative models in this paper. Firstly, historical data are used to train a denoising diffusion probabilistic model (DDPM) to generate data. Secondly, both the training set and the generated data are input to an autoencoder, and a data evaluation metric is constructed to filter high-quality out of distribution features. Subsequently, positive and negative sample pairs are constructed based on these features, and an improved supervised contrastive learning detection model is designed to extract unique features of normal data under the supervision of virtual fault samples. Finally, the effectiveness and superiority of the proposed method are validated through the Tennessee Eastman simulation process.
| Item Type: | Article |
|---|---|
| Additional Information: | ** Article version: AM ** Embargo end date: 31-12-9999 ** From Elsevier via Jisc Publications Router ** History: accepted 06-12-2024; issued 09-12-2024. ** Licence for AM version of this article: This article is under embargo with an end date yet to be finalised. |
| SWORD Depositor: | JISC Router |
| Depositing User: | JISC Router |
| Date Deposited: | 18 Dec 2024 12:20 |
| Last Modified: | 18 Dec 2024 12:21 |
| URI: | https://bnu.repository.guildhe.ac.uk/id/eprint/19470 |
Actions (login required)
 |
Edit Item |