期刊
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
卷 46, 期 12, 页码 1664-1674出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSMC.2016.2605159
关键词
Deep learning; distributed parameter system (DPS); model reduction; restricted Boltzmann machine (RBM); spatiotemporal dynamics
资金
- Research Grants Council of Hong Kong [11205615, 11207714]
- Guangdong Government [2016A010102016]
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据