We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Process structure-based recurrent neural network modeling for predictive control: A comparative study.
- Authors
Alhajeri, Mohammed S.; Luo, Junwei; Wu, Zhe; Albalawi, Fahad; Christofides, Panagiotis D.
- Abstract
• Development of process structure-award RNN models. • RNN model training using plant data from an ASPEN simulator. • MPC design using various RNN models and implementation to ASPEN simulator. • Evaluation of MPC performance and computational time. Recurrent neural networks (RNN) have demonstrated their ability in providing a remarkably accurate modeling approximation to describe the dynamic evolution of complex, nonlinear chemical processes in several applications. Although conventional fully-connected RNN models have been successfully utilized in model predictive control (MPC) to regulate chemical processes with desired approximation accuracy, the development of RNN models in terms of model structure can be further improved by incorporating physical knowledge to achieve better accuracy and computational efficiency. This work investigates the performance of MPC based on two different RNN structures. Specifically, a fully-connected RNN model, and a partially-connected RNN model developed using a prior physical knowledge, are considered. This study uses an example of a large-scale complex chemical process simulated by Aspen Plus Dynamics to demonstrate improvements in the RNN model and an RNN-based MPC performance, when the prior knowledge of the process is taken into account.
- Subjects
RECURRENT neural networks; ARTIFICIAL neural networks; PREDICTION models; CHEMICAL processes; COMPARATIVE studies
- Publication
Chemical Engineering Research & Design: Transactions of the Institution of Chemical Engineers Part A, 2022, Vol 179, p77
- ISSN
0263-8762
- Publication type
Article
- DOI
10.1016/j.cherd.2021.12.046