Uncertainty-aware soft sensor using Bayesian recurrent neural networks
- Authors
- Lee, Minjung; Bae, Jinsoo; Kim, Seoung Bum
- Issue Date
- Oct-2021
- Publisher
- ELSEVIER SCI LTD
- Keywords
- Bayesian deep learning; Recurrent neural networks; Soft sensor; Uncertainty
- Citation
- ADVANCED ENGINEERING INFORMATICS, v.50
- Indexed
- SCIE
SCOPUS
- Journal Title
- ADVANCED ENGINEERING INFORMATICS
- Volume
- 50
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/136180
- DOI
- 10.1016/j.aei.2021.101434
- ISSN
- 1474-0346
- Abstract
- Data-driven soft sensors have been widely used to measure key variables for industrial processes. Soft sensors using deep learning models have attracted considerable attention and shown superior predictive performance. However, if a soft sensor encounters an unexpected situation in inferring data or if noisy input data is used, the estimated value derived by a standard soft sensor using deep learning may at best be untrustworthy. This problem can be mitigated by expressing a degree of uncertainty about the trustworthiness of the estimated value produced by the soft sensor. To address this issue of uncertainty, we propose using an uncertainty-aware soft sensor that uses Bayesian recurrent neural networks (RNNs). The proposed soft sensor uses a RNN model as a backbone and is then trained using Bayesian techniques. The experimental results demonstrated that such an uncertainty-aware soft sensor increases the reliability of predictive uncertainty. In comparisons with a standard soft sensor, it shows a capability to use uncertainties for interval prediction without compromising predictive performance.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > School of Industrial and Management Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.