Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.7
3.5
Journals
Processes
Special Issues
Machine Learning in Model Predictive Control and Optimal Control
share announcement

Machine Learning in Model Predictive Control and Optimal Control

A special issue of Processes (ISSN 2227-9717). This special issue belongs to the section "Automation Control Systems".

Deadline for manuscript submissions: closed (20 November 2023) | Viewed by 8199

Special Issue Editors

Dr. Zhe Wu

E-Mail Website
Guest Editor
Chemical and Biomolecular Engineering, National University of Singapore, Singapore 117585, Singapore
Interests: chemical process control; model predictive control; machine learning
Special Issues, Collections and Topics in MDPI journals
Dr. Xunyuan Yin

E-Mail Website
Guest Editor
School of Chemical and Biomedical Engineering, Nanyang Technological University, Singapore, Singapore
Interests: state estimation; process monitoring; process decomposition
Dr. Yan Qin

E-Mail Website
Guest Editor
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore
Interests: data-driven process monitoring; data-driven soft-sensor modeling; machine learning; remaining useful life estimation; digital twin
Prof. Dr. Xiaodong Xu

E-Mail Website
Guest Editor
Department of Automation, Central South University, Changsha, China
Interests: optimal control; state estimation; operation strategies; leak detection; model-based fault detection; robust output regulation; model predictive control

Special Issue Information

Dear Colleagues,

Machine learning (ML) creates new paradigms and opportunities in the design of advanced process control systems for chemical processes. While machine learning techniques such as neural networks and reinforcement learning have been successfully applied to model predictive control (MPC) and optimal control schemes, a variety of theoretical issues, such as stability, robustness, and optimality, as well as some practical challenges such as data limitation and computational efficiency need to be addressed. This Special Issue intends to provide a platform for researchers and practitioners to share state-of-the-art algorithms and methods for both theory and application works to address some of the aforementioned fundamental challenges associated with using machine learning in MPC and optimal control.

Potential topics include, but are not limited to:

  • Novel ML methods for model development and theoretical analysis on the generalization performance of ML models;
  • Theoretical methodologies and applications of predictive control and optimal control using machine learning techniques;
  • ML in parameter and state estimation, fault detection, soft sensing, and their applications in MPC and optimal control;
  • Computational development of ML-based MPC and optimal control systems to address practical challenges such as computational efficiency, feasibility for large-scale systems, etc.

Dr. Zhe Wu
Dr. Xunyuan Yin
Dr. Yan Qin
Prof. Dr. Xiaodong Xu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Processes is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • machine learning
  • model predictive control
  • optimal control
  • artificial intelligence
  • neural networks
  • reinforcement learning
  • chemical process control

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

28 pages, 902 KiB  
Article
A Proposed Methodology to Evaluate Machine Learning Models at Near-Upper-Bound Predictive Performance—Some Practical Cases from the Steel Industry
by Leo S. Carlsson and Peter B. Samuelsson
Processes 2023, 11(12), 3447; https://doi.org/10.3390/pr11123447 - 18 Dec 2023
Viewed by 699
Abstract
The present work aims to answer three essential research questions (RQs) that have previously not been explicitly dealt with in the field of applied machine learning (ML) in steel process engineering. RQ1: How many training data points are needed to create a model [...] Read more.
The present work aims to answer three essential research questions (RQs) that have previously not been explicitly dealt with in the field of applied machine learning (ML) in steel process engineering. RQ1: How many training data points are needed to create a model with near-upper-bound predictive performance on test data? RQ2: What is the near-upper-bound predictive performance on test data? RQ3: For how long can a model be used before its predictive performance starts to decrease? A methodology to answer these RQs is proposed. The methodology uses a developed sampling algorithm that samples numerous unique training and test datasets. Each sample was used to create one ML model. The predictive performance of the resulting ML models was analyzed using common statistical tools. The proposed methodology was applied to four disparate datasets from the steel industry in order to externally validate the experimental results. It was shown that the proposed methodology can be used to answer each of the three RQs. Furthermore, a few findings that contradict established ML knowledge were also found during the application of the proposed methodology. Full article
(This article belongs to the Special Issue Machine Learning in Model Predictive Control and Optimal Control)
►▼ Show Figures

Figure 1

19 pages, 5040 KiB  
Article
RNN-LSTM-Based Model Predictive Control for a Corn-to-Sugar Process
by Jiaqi Meng, Chengbo Li, Jin Tao, Yi Li, Yi Tong, Yu Wang, Lei Zhang, Yachao Dong and Jian Du
Processes 2023, 11(4), 1080; https://doi.org/10.3390/pr11041080 - 3 Apr 2023
Cited by 2 | Viewed by 1700
Abstract
The corn-to-sugar process is difficult to control automatically because of the complex physical and chemical phenomena involved. Because the RNN-LSTN model has been shown to handle long-term time dependencies well, this article focused on the design of a model predictive control system based [...] Read more.
The corn-to-sugar process is difficult to control automatically because of the complex physical and chemical phenomena involved. Because the RNN-LSTN model has been shown to handle long-term time dependencies well, this article focused on the design of a model predictive control system based on this machine learning model. Based on the historical data, we first reduced the input variable dimension through data preprocessing, data dimension reduction, sensitivity analysis, etc., and then the RNN-LSTM model, with these identified key sites as inputs, and the dextrose equivalent value as the output, was constructed. Then, through model predictive control using the locally linearized RNN-LSTM as the predictive model, the objective value of the dextrose equivalent was successfully controlled at the target value by our simulation study, in different situations of setpoint changes and disturbances. This showed the potential of applying RNN-LSTM-Based model predictive control in a corn-to-sugar process. Full article
(This article belongs to the Special Issue Machine Learning in Model Predictive Control and Optimal Control)
►▼ Show Figures

Figure 1

19 pages, 4443 KiB  
Article
Achieving Optimal Paper Properties: A Layered Multiscale kMC and LSTM-ANN-Based Control Approach for Kraft Pulping
by Parth Shah, Hyun-Kyu Choi and Joseph Sang-Il Kwon
Processes 2023, 11(3), 809; https://doi.org/10.3390/pr11030809 - 8 Mar 2023
Cited by 18 | Viewed by 1401
Abstract
The growing demand for various types of paper highlights the importance of optimizing the kraft pulping process to achieve desired paper properties. This work proposes a novel multiscale model to optimize the kraft pulping process and obtain desired paper properties. The model combines [...] Read more.
The growing demand for various types of paper highlights the importance of optimizing the kraft pulping process to achieve desired paper properties. This work proposes a novel multiscale model to optimize the kraft pulping process and obtain desired paper properties. The model combines mass and energy balance equations with a layered kinetic Monte Carlo (kMC) algorithm to predict the degradation of wood chips, the depolymerization of cellulose, and the spatio-temporal evolution of the Kappa number and cellulose degree of polymerization (DP). A surrogate LSTM-ANN model is trained on data generated from the multiscale model under different operating conditions, dealing with both time-varying and time-invariant inputs, and an LSTM-ANN-based model predictive controller is designed to achieve desired set-point values of the Kappa number and cellulose DP while considering process constraints. The results show that the LSTM-ANN-based controller is able to drive the process to desired set-point values with the use of a computationally faster surrogate model with high accuracy and low offset. Full article
(This article belongs to the Special Issue Machine Learning in Model Predictive Control and Optimal Control)
►▼ Show Figures

Figure 1

22 pages, 961 KiB  
Article
Are Neural Networks the Right Tool for Process Modeling and Control of Batch and Batch-like Processes?
by Mustafa Rashid and Prashant Mhaskar
Processes 2023, 11(3), 686; https://doi.org/10.3390/pr11030686 - 24 Feb 2023
Cited by 1 | Viewed by 1427
Abstract
The prevalence of batch and batch-like operations, in conjunction with the continued resurgence of artificial intelligence techniques for clustering and classification applications, has increasingly motivated the exploration of the applicability of deep learning for modeling and feedback control of batch and batch-like processes. [...] Read more.
The prevalence of batch and batch-like operations, in conjunction with the continued resurgence of artificial intelligence techniques for clustering and classification applications, has increasingly motivated the exploration of the applicability of deep learning for modeling and feedback control of batch and batch-like processes. To this end, the present study seeks to evaluate the viability of artificial intelligence in general, and neural networks in particular, toward process modeling and control via a case study. Nonlinear autoregressive with exogeneous input (NARX) networks are evaluated in comparison with subspace models within the framework of model-based control. A batch polymethyl methacrylate (PMMA) polymerization process is chosen as a simulation test-bed. Subspace-based state-space models and NARX networks identified for the process are first compared for their predictive power. The identified models are then implemented in model predictive control (MPC) to compare the control performance for both modeling approaches. The comparative analysis reveals that the state-space models performed better than NARX networks in predictive power and control performance. Moreover, the NARX networks were found to be less versatile than state-space models in adapting to new process operation. The results of the study indicate that further research is needed before neural networks may become readily applicable for the feedback control of batch processes. Full article
(This article belongs to the Special Issue Machine Learning in Model Predictive Control and Optimal Control)
►▼ Show Figures

Figure 1

23 pages, 972 KiB  
Article
Economic Model Predictive Control of Nonlinear Systems Using Online Learning of Neural Networks
by Cheng Hu, Scarlett Chen and Zhe Wu
Processes 2023, 11(2), 342; https://doi.org/10.3390/pr11020342 - 20 Jan 2023
Cited by 3 | Viewed by 1674
Abstract
This work focuses on the development of a Lyapunov-based economic model predictive control (LEMPC) scheme that utilizes recurrent neural networks (RNNs) with an online update to optimize the economic benefits of switched non-linear systems subject to a prescribed switching schedule. We first develop [...] Read more.
This work focuses on the development of a Lyapunov-based economic model predictive control (LEMPC) scheme that utilizes recurrent neural networks (RNNs) with an online update to optimize the economic benefits of switched non-linear systems subject to a prescribed switching schedule. We first develop an initial offline-learning RNN using historical operational data, and then update RNNs with real-time data to improve model prediction accuracy. The generalized error bounds for RNNs updated online with independent and identically distributed (i.i.d.) and non-i.i.d. data samples are derived, respectively. Subsequently, by incorporating online updating RNNs within LEMPC, probabilistic closed-loop stability, and economic optimality are achieved simultaneously for switched non-linear systems accounting for the RNN generalized error bound. A chemical process example with scheduled mode transitions is used to demonstrate that the closed-loop economic performance under LEMPC can be improved using an online update of RNNs. Full article
(This article belongs to the Special Issue Machine Learning in Model Predictive Control and Optimal Control)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop