Back to Search
Start Over
Deep Learning-Based Model Reduction for Distributed Parameter Systems.
- Source :
- IEEE Transactions on Systems, Man & Cybernetics. Systems; Dec2016, Vol. 46 Issue 12, p1664-1674, 11p
- Publication Year :
- 2016
-
Abstract
- This paper presents a deep learning-based model reduction method for distributed parameter systems (DPSs). The proposed method includes three phases. In phase I, numerical or experimental data of the spatiotemporal distribution is reduced into low-dimensional representations using the deep auto-encoder (DAE). In phase II, the low-dimensional representations are used to establish the reduced-order model. In phase III, the reduced model is then used to reconstruct the high-dimensional DPS. Experimental studies are conducted to validate the proposed method. The proposed method is compared with the classical proper orthogonal decomposition method and demonstrates better modeling accuracy and efficiency in the experiments. [ABSTRACT FROM PUBLISHER]
- Subjects :
- DEEP learning
DISTRIBUTED parameter systems
BOLTZMANN machine
Subjects
Details
- Language :
- English
- ISSN :
- 21682216
- Volume :
- 46
- Issue :
- 12
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Systems, Man & Cybernetics. Systems
- Publication Type :
- Academic Journal
- Accession number :
- 119593165
- Full Text :
- https://doi.org/10.1109/TSMC.2016.2605159