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
Model Learning Predictive Control for Industrial Processes
share announcement

Model Learning Predictive Control for Industrial Processes

A special issue of Processes (ISSN 2227-9717). This special issue belongs to the section "Process Control and Monitoring".

Deadline for manuscript submissions: closed (15 February 2022) | Viewed by 4809

Special Issue Editors

Dr. Leyla Özkan

E-Mail Website
Guest Editor
Control Systems Group, Department of Electrical Engineering, De Zaale, 5612 AJ Eindhoven, The Netherlands
Interests: modeling for control; model-based operation support technology; integration of design and control; dynamic operation; model reduction
Dr. Alejandro Marquez Ruiz

E-Mail Website
Guest Editor
Control Systems Group, Department of Electrical Engineering, De Zaale, 5612 AJ Eindhoven, The Netherlands
Interests: model predictive control; model-based control; modeling for control; model reduction; model based operation support technology

Special Issue Information

Dear Colleagues,

Model-based operation support technology, specifically (linear) model predictive control, has a long history in the chemical industry and is a standard technology for multivariable and constrained control problems which have been successfully implemented in refineries and petrochemicals. The implementation of such technology results in substantial economic benefits while fulling the operational conditions and product specifications. Despite such benefits, the lifetime performance of this technology can be limited. As in any model-based technology, the closed loop performance highly depends on how accurately the chemical plant is modeled. Changes in plant behavior or operating conditions necessitate maintenance in the form of identification of a new model or adjustment of control design to new conditions, resulting in a high level of autonomy for MPC technology.

Nevertheless, there is a growing momentum in recent years in the digital transformation of manufacturing industries as part of Industry 4.0. Chemical industries are also embracing this change using artificial intelligence, sensors, big data, and the Internet of Things, moving toward a ‘smart factory’ that ‘learns‘ and ‘adapts’. Although learning is not new in chemical process control as in the case of iterative learning control of batch processes, recent research efforts have focused on purely learning optimal control strategies (model free), directly using process data as a way to mitigate from expensive modeling campaign.

In this Special Issue, we cordially invite your contributions that will feature the latest developments in model-predictive control with regard to bringing a high level of autonomy in the technology but also controlling approaches that combine learning methods using data. Contributions that show applications on pilot plants or actual chemical processes are particularly welcome.

Dr. Leyla Özkan
Dr. Alejandro Marquez Ruiz
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 papers will be 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 2000 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

  • Model Learning
  • Model predictive control
  • Iterative learning control
  • Machine learning
  • Batch processing
  • Reinforcement learning
  • Autonomous operation, self-learning
  • Adaptive control

Published Papers (2 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

24 pages, 3141 KiB  
Article
Offset-Free Economic MPC Based on Modifier Adaptation: Investigation of Several Gradient-Estimation Techniques
by Marco Vaccari, Dominique Bonvin, Federico Pelagagge and Gabriele Pannocchia
Processes 2021, 9(5), 901; https://doi.org/10.3390/pr9050901 - 20 May 2021
Cited by 9 | Viewed by 1868
Abstract
Various offset-free economic model predictive control schemes that include a disturbance model and the modifier-adaptation principle have been proposed in recent years. These schemes are able to reach plant optimality asymptotically even in the presence of plant–model mismatch. All schemes are affected by [...] Read more.
Various offset-free economic model predictive control schemes that include a disturbance model and the modifier-adaptation principle have been proposed in recent years. These schemes are able to reach plant optimality asymptotically even in the presence of plant–model mismatch. All schemes are affected by a major issue that is common to all modifier-adaptation formulations, namely, plant optimality (note that convergence per se does not require perfect plant gradients) requires perfect knowledge of static plant gradients, which is a piece of information not known in most practical applications. To address this issue, we present two gradient-estimation techniques, one based on Broyden’s update and the other one on linear regression. We apply these techniques for the estimation of either the plant gradients or the modifiers directly. The resulting economic MPC schemes are tested in a simulation and compared on two benchmark examples of different complexity with respect to both convergence speed and robustness to measurement noise. Full article
(This article belongs to the Special Issue Model Learning Predictive Control for Industrial Processes)
►▼ Show Figures

Figure 1

25 pages, 10126 KiB  
Article
Model-Based Evaluation of a Data-Driven Control Strategy: Application to Ibuprofen Crystallization
by Frederico C. C. Montes, Merve Öner, Krist V. Gernaey and Gürkan Sin
Processes 2021, 9(4), 653; https://doi.org/10.3390/pr9040653 - 8 Apr 2021
Cited by 5 | Viewed by 1801
Abstract
This work presents a methodology that relies on the application of the radial basis functions network (RBF)-based feedback control algorithms to a pharmaceutical crystallization process. Within the scope of the model-based evaluation of the proposed strategy, firstly strategies for the data treatment, data [...] Read more.
This work presents a methodology that relies on the application of the radial basis functions network (RBF)-based feedback control algorithms to a pharmaceutical crystallization process. Within the scope of the model-based evaluation of the proposed strategy, firstly strategies for the data treatment, data structure and the training methods reflecting the possible scenarios in the industry (Moving Window, Growing Window and Golden Batch strategies) were introduced. This was followed by the incorporation of such RBF strategies within a soft sensor application and a nonlinear predictive data-driven control application. The performance of the RBF control strategies was tested for the undisturbed cases as well as in the presence of disturbances in the process. The promising results from both RBF soft sensor control and the RBF predictive control demonstrated great potential of these techniques for the control of the crystallization process. In particular, both Moving Window and Golden Batch strategies performed the best results for an RBF soft sensor, and the Growing Window outperformed the remaining methodologies for predictive control. Full article
(This article belongs to the Special Issue Model Learning Predictive Control for Industrial Processes)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop