A tutorial review of neural network modeling approaches for model predictive control

Ren, Yi; Alhajeri, Mohammed S.; Liu, Junwei; Chen, Scarlett; Abdullah, Fahim; Wu, Zhe; Christofides, Panagiotis D.

doi:10.1016/j.compchemeng.2022.107956

Cited by 62 publications

(22 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, DABNet is treated as one of the benchmark data-driven network-based models for evaluating the performance of the proposed architectures in this work. Furthermore, the proposed network structures are compared with a couple of other widely used data-driven models for system identification and the LSTM-type and the Gated Recurrent Unit (GRU)-type RNNs. , For three case studies considered in this work, performances of the proposed hybrid series and parallel network models have been compared with those of LSTMs, GRUs, and DABNet, in addition to the comparison with respect to the static-only and dynamic-only network architectures.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Series/Parallel All-Nonlinear Dynamic-Static Neural Networks: Development, Training, and Application to Chemical Processes

Mukherjee

Bhattacharyya

2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

This paper presents the development of data-driven hybrid nonlinear static-nonlinear dynamic neural network models and addresses the challenges of optimal estimation of parameters for such hybrid networks. A parallel static-dynamic neural network and two variants of series networks, specifically, nonlinear static-nonlinear dynamic and nonlinear dynamic-nonlinear static networks, are investigated in this work. Performances of the proposed fully nonlinear hybrid series and parallel network models are compared with the existing state-of-the-art data-driven models like long−short-term memory networks and gated recurrent unit models as well as DABNet-type linear-dynamic-nonlinear-static neural network. Algorithms are developed for training the series and parallel hybrid networks where the static and dynamic networks can be trained independently by different algorithms. These algorithms offer flexibility for incorporating different types of static and dynamic network architectures and their training algorithms thus offering tradeoff between computational expense and accuracy for highly nonlinear systems. In addition to the typical training objective that minimizes some squared error, an objective function is considered that penalizes overfitting and uncertainty in parameter estimates. Performances of the proposed algorithms are evaluated for three nonlinear example problems�a two-tank pH neutralization reactor, the widely used Van de Vusse reactor, and a pilot plant for postcombustion CO 2 capture using monoethanolamine solvent. Computational expense and convergence performance of the proposed network architectures and their training algorithms are presented.

show abstract

Section: Introductionmentioning

confidence: 99%

Hybrid Series/Parallel All-Nonlinear Dynamic-Static Neural Networks: Development, Training, and Application to Chemical Processes

Mukherjee

Bhattacharyya

2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…Due to the ability to capture nonlinear dynamics, RNNs have been developed for various applications. [1][2][3][4][5] For example, deep neural networks were utilized to capture the dynamic behavior of complex chemical processes in Bangi and Kwon, Bhadriraju et al, Lee et al, and Shah et al [6][7][8][9] RNNs were developed and integrated into model predictive controller (MPC) for pharmaceutical manufacturing processes in Wong et al and Zheng et al 2,5 More recently, in Ren et al, 1 a tutorial review of neural network modeling of nonlinear dynamic systems and the incorporation of neural network models into MPC was presented. While machine learning provides an efficient modeling tool for nonlinear, complex manufacturing processes, the majority of ML modeling work is done for individual processes using historical data collected from the specific process of interest, and cannot be transferred to a broad class of processes with similar configurations.…”

Section: Introductionmentioning

confidence: 99%

“…Recurrent neural networks (RNNs) have been widely used in modeling nonlinear dynamic systems using sequential or time‐series data. Due to the ability to capture nonlinear dynamics, RNNs have been developed for various applications 1–5 . For example, deep neural networks were utilized to capture the dynamic behavior of complex chemical processes in Bangi and Kwon, Bhadriraju et al, Lee et al, and Shah et al 6–9 RNNs were developed and integrated into model predictive controller (MPC) for pharmaceutical manufacturing processes in Wong et al and Zheng et al 2,5 More recently, in Ren et al, 1 a tutorial review of neural network modeling of nonlinear dynamic systems and the incorporation of neural network models into MPC was presented.…”

Section: Introductionmentioning

confidence: 99%

Modeling and predictive control of nonlinear processes using transfer learning method

Xiao

2023

AIChE Journal

Self Cite

View full text Add to dashboard Cite

This work develops a transfer learning (TL) framework for modeling and predictive control of nonlinear systems using recurrent neural networks (RNNs) with the knowledge obtained in modeling one process transferred to another. Specifically, transfer learning uses a pretrained model developed based on a source domain as the starting point, and adapts the model to a target process with similar configurations. The generalization error for TL‐based RNN (TL‐RNN) is first derived to demonstrate the generalization capability on the target process. The theoretical error bound that depends on model capacity and the discrepancy between source and target domains is then utilized to guide the development of pretrained models for improved model transferability. Subsequently, the TL‐RNN model is utilized as the prediction model in model predictive controller (MPC) for the target process. Finally, the simulation study of chemical reactors via Aspen Plus Dynamics is used to demonstrate the benefits of transfer learning.

show abstract

“…It is a highly flexible and powerful control scheme that permits the inclusion of practical constraints (e.g., temperature limits of a heating jacket) on the manipulated variables, thereby facilitating the search of feasible solutions to optimization-based control problems by respecting any physical limits imposed. Collectively, the convergence of next-generation information technologies and the pervasive nature of data in modern manufacturing complexes culminates in machine learning-based MPC (ML-MPC), which has attracted an increased level of attention in recent years, and is gaining traction in control of highly nonlinear processes. − In ref an ML-MPC is developed using an autoencoder-based recurrent neural network (RNN) to control the batch crystallization process, where the crystal size and yield are optimized. Additionally, the ML-MPC scheme is equipped with an error-triggered online update mechanism to mitigate issues pertaining to plant-model mismatch and to improve the overall control performance .…”

Section: Introductionmentioning

confidence: 99%

Physics-Informed Online Machine Learning and Predictive Control of Nonlinear Processes with Parameter Uncertainty

Zheng

2023

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

In this work, we present a physics-informed recurrent neural network (PIRNN)-based modeling approach for nonlinear dynamic systems with parameter uncertainty. Physics-informed modeling approaches can improve the generalization performance of machine learning models by embedding the knowledge of physical laws in the learning process. Based on the standard PIRNN modeling approach for the nominal system without model uncertainties, we develop a novel PIRNN-enhanced modeling method that integrates online estimation of uncertain process parameters into the training process using the latest process data. The PIRNN-enhanced modeling approach is incorporated into the design of model predictive control (MPC), where an error-triggered mechanism is employed to trigger the quantification of modeling uncertainties and update of PIRNN models accordingly. Finally, a chemical process example is used to demonstrate the superiority of the proposed PIRNN-enhanced online learning mechanism in comparison to the conventional purely data-driven online update strategy for nonlinear systems subject to process parameter uncertainty.

show abstract

A tutorial review of neural network modeling approaches for model predictive control

Cited by 62 publications

References 71 publications

Hybrid Series/Parallel All-Nonlinear Dynamic-Static Neural Networks: Development, Training, and Application to Chemical Processes

Hybrid Series/Parallel All-Nonlinear Dynamic-Static Neural Networks: Development, Training, and Application to Chemical Processes

Modeling and predictive control of nonlinear processes using transfer learning method

Physics-Informed Online Machine Learning and Predictive Control of Nonlinear Processes with Parameter Uncertainty

Contact Info

Product

Resources

About