We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
On generalization error of neural network models and its application to predictive control of nonlinear processes.
- Authors
Alhajeri, Mohammed S.; Alnajdi, Aisha; Abdullah, Fahim; Christofides, Panagiotis D.
- Abstract
In order to approximate nonlinear dynamic systems utilizing time-series data, recurrent neural networks (RNNs) and long short-term memory (LSTM) networks have frequently been used. The training error of neural networks may often be made suitably modest; however, the accuracy can be further improved by incorporating prior knowledge in the construction of machine learning-based models. Specifically, physics-based RNN modeling has yielded more reliable RNN models than traditional RNNs. Yet, a framework for constructing and assessing the generalization ability of such RNN models as well as LSTM models to be utilized in model predictive control (MPC) systems is lacking. In this work, we develop a methodological framework to quantify the generalization error bounds for partially-connected RNNs and LSTM models. The partially-connected RNN model is then utilized to predict the state evolution in a MPC scheme. We illustrate through open-loop and closed-loop simulations of a nonlinear chemical process of two reactors-in-series that the proposed approach provides a flexible framework for leveraging both prior knowledge and data, thereby improving the performance significantly when compared to a fully-connected modeling approach under Lyapunov-based MPC. • ML model generalization error bounds are calculated. • Fully-connected and partially-connected ML models are studied. • ML model is used in model predictive control. • Application to a chemical process example is carried out.
- Subjects
ARTIFICIAL neural networks; PREDICTIVE control systems; MACHINE learning; RECURRENT neural networks; STIMULUS generalization; NONLINEAR dynamical systems
- Publication
Chemical Engineering Research & Design: Transactions of the Institution of Chemical Engineers Part A, 2023, Vol 189, p664
- ISSN
0263-8762
- Publication type
Article
- DOI
10.1016/j.cherd.2022.12.001