Machine learning-based reduced-order modeling and predictive control of nonlinear processes

Zhao, Tianyi; Zheng, Yingzhe; Gong, Jie; Wu, Zhe

doi:10.1016/j.cherd.2022.02.005

Cited by 28 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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

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

show abstract

“…This effectively reduces the number of neurons and layers required by the RNN model to fit the data in the lower-dimensional latent space and thereby further enhance its computational efficiency. In general, the AE is beneficial for analyzing data sets with a substantial number of features and has found promising application as a model reduction technique for data-driven modeling approaches in different domains (e.g., catalytic tubular reactor system identification, malware detection, image recognition and classification, , and control of a diffusion-reaction process). However, the incorporation of an AE in machine-learning-based MPC to improve the computational efficiency of the machine-learning-based control of batch crystallization systems characterized via the high-dimensional PBM and solved via the classes method, to the best of the authors’ knowledge, has not been previously reported.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Modeling and Predictive Control of the Batch Crystallization Process

Zheng

Wang

2022

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

This work develops a framework for building machine learning models and machine-learning-based predictive control schemes for batch crystallization processes. We consider a seeded fesoterodine fumarate cooling crystallization and dissolution process in a batch reactor and present the methodology and implementation of simulation, modeling, and controller design. Specifically, to address the experimental data scarcity problem, we first develop a one-dimensional population balance model based on published kinetic parameters that were obtained empirically to describe the formation of crystals via nucleation, growth, and agglomeration. Then, recurrent neural network (RNN) and autoencoder−RNN (AERNN) models are developed using data from extensive open-loop simulations of the semi-empirical population balance model under various operating conditions to capture the process dynamic behavior. Two model predictive control (MPC) schemes using the respective RNN and AERNN models are developed to optimize the crystallization process with respect to product yield, crystal size, number of fines in the final product, and energy consumption, while accounting for the constraints on manipulated inputs. Through open-and closed-loop simulations, it is demonstrated that the RNN and AERNN models capture the process dynamics well, and the RNN-and AERNN-based MPCs achieved the desired product yield and crystal size with significantly improved computational efficiency.

show abstract

“…5 Additionally, the autoencoder (AE) neural network, which is an unsupervised dimensionality reduction technique that minimizes modeling complexity while still maintaining an adequate model fidelity, can be integrated with RNN to further enhance its computational efficiency. Several recent works have utilized RNN and AE-based RNN (AERNN) as surrogate process models in MPCs to control chemical plants in real time and optimize process performance accounting for closed-loop stability, safety, and control actuator constraints, which demonstrated superior computational efficiency compared to using the conventional first-principles model-based MPCs in their implementation to a diffusion-reaction process, 6 a batch crystallization process, 7 and a plasma etch process. 8 However, although pre-trained machine learning models have exhibited desirable computational properties and have shown to be promising substitutions for first-principles models in MPC, uncertainties in crystallization kinetics including intrinsic and exogenous uncertainties could be of major concern to their applications to real chemical processes, which can result in performance deterioration of these MPC schemes over time.…”

Section: Introductionmentioning

confidence: 99%

“…Additionally, the autoencoder (AE) neural network, which is an unsupervised dimensionality reduction technique that minimizes modeling complexity while still maintaining an adequate model fidelity, can be integrated with RNN to further enhance its computational efficiency. Several recent works have utilized RNN and AE‐based RNN (AERNN) as surrogate process models in MPCs to control chemical plants in real time and optimize process performance accounting for closed‐loop stability, safety, and control actuator constraints, which demonstrated superior computational efficiency compared to using the conventional first‐principles model‐based MPCs in their implementation to a diffusion–reaction process, 6 a batch crystallization process, 7 and a plasma etch process 8 …”

Section: Introductionmentioning

confidence: 99%

Online learning‐based predictive control of crystallization processes under batch‐to‐batch parametric drift

et al. 2022

Self Cite

View full text Add to dashboard Cite

This work considers a seeded fesoterodine fumarate (FF) cooling crystallization and presents the methodology and implementation of a real‐time machine learning modeling‐based predictive controller to handle batch‐to‐batch (B2B) parametric drift. Specifically, an autoencoder recurrent neural network‐based model predictive controller (AERNN‐MPC) is developed to optimize product yield, crystal size, and energy consumption while accounting for the physical constraints on cooling jacket temperature. Deviations in the kinetic parameters are considered in the closed‐loop simulations to account for the B2B parametric drift, and two error‐triggered online update mechanisms are proposed to address issues pertaining to the availability of real‐time crystal property measurements and are incorporated into the AERNN‐MPC to improve the model prediction accuracy. Closed‐loop simulation results demonstrate that the proposed AERNN‐MPC with online update, irrespective of the accessibility to real‐time crystal property data, achieves a desired closed‐loop performance in terms of maximizing product yield and minimizing energy consumption.

show abstract

Machine learning-based reduced-order modeling and predictive control of nonlinear processes

Cited by 28 publications

References 21 publications

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

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

Machine Learning Modeling and Predictive Control of the Batch Crystallization Process

Online learning‐based predictive control of crystallization processes under batch‐to‐batch parametric drift

Contact Info

Product

Resources

About