Control Applications and Learning

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Systems & Control Engineering".

Deadline for manuscript submissions: closed (28 February 2022) | Viewed by 12021

Special Issue Editors


E-Mail Website
Guest Editor
Division of Mechanical Engineering, Korea Maritime and Ocean University, Busan 49112, Republic of Korea
Interests: robotics and control; artificial intelligence; humanoid robots; Unmanned Underwater Vehicles; robust control; ultra-high-speed control
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The proper design of controllers for various kinds of systems involving unknown conditions and highly nonlinear and uncertain dynamics remains an open research topic. Meanwhile, machine-learning-based algorithms have been used in several fields, especially when massive amounts of data and great computing power are needed. Research in the field of machine learning aiming to solve issues of flexibility and complexity is ongoing. The connection between (modern) control theory and machine learning is very important in view of surpassing the potentialities of each discipline.

On this note, "control and learning" techniques are presently used in the driving technology underpinning a whole new generation of autonomous devices and cognitive artifacts that, through their learning capabilities, interact seamlessly with the world around them, hence providing the missing link between the digital and physical worlds.

Moreover, control and learning techniques are often used in various industries for control, fault detection, fault diagnosis, and fault-tolerant control. To address these issues, there is a need to develop hybrid algorithms based on control and/or learning; such algorithms can be recommended in this Special Issue.

This Special Issue will focus on control, modeling, various machine learning techniques, fault diagnosis, and fault-tolerant control for systems. Papers specifically addressing the theoretical, experimental, practical, and technological aspects of modeling, control, fault diagnosis, and fault-tolerant control of various systems and extending concepts and methodologies from classical techniques to hybrid methods will be highly suitable for this Special Issue. Potential themes include, but are not limited to:

  • Modeling and identification
  • Adaptive and hybrid control
  • Adaptive and hybrid observers
  • Reinforcement learning for control
  • Data-driven control
  • Fault diagnosis
  • Fault-tolerant control of systems based on various control and learning techniques

Prof. Dr. Jong-Myon Kim
Prof. Dr. Hyeung-Sik Choi
Dr. Farzin Piltan
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. Electronics is an international peer-reviewed open access semimonthly 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

  • robust/nonlinear control algorithms
  • machine learning algorithms
  • system modeling and identification techniques
  • fault diagnosis/prognosis and fault-tolerant control using hybrid techniques
  • adaptive and hybrid control techniques
  • adaptive and hybrid observation techniques
  • reinforcement learning for control
  • data-driven control

Published Papers (4 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

18 pages, 2502 KiB  
Article
Robust Model Predictive Controller Using Recurrent Neural Networks for Input–Output Linear Parameter Varying Systems
by Mohsen Hadian, Amin Ramezani and Wenjun Zhang
Electronics 2021, 10(13), 1557; https://doi.org/10.3390/electronics10131557 - 28 Jun 2021
Cited by 6 | Viewed by 2004
Abstract
This paper develops a model predictive controller (MPC) for constrained nonlinear MIMO systems subjected to bounded disturbances. A linear parameter varying (LPV) model assists MPC in dealing with nonlinear dynamics. In this study, the nonlinear process is represented by an LPV using past [...] Read more.
This paper develops a model predictive controller (MPC) for constrained nonlinear MIMO systems subjected to bounded disturbances. A linear parameter varying (LPV) model assists MPC in dealing with nonlinear dynamics. In this study, the nonlinear process is represented by an LPV using past input–output information (LPV-IO). Two primary objectives of this study are to reduce online computational load compared with the existing literature of MPC with an LPV-IO model and to confirm the robustness of the controller in the presence of disturbance. For the first goal, a recurrent neural network (RNN) is employed to solve real-time optimization problems with lower online computation. Regarding robustness, a new control law is developed, which comprises a fixed control gain (K) and a free perturbation (C). The proposed method enjoys a shrunken conservatism owing to the finding of a larger possible terminal region and using free control moves. The strategy is examined in an alkylation of benzene process and displays outstanding performance in both setpoint tracking and disturbance rejection problems. Moreover, the superiority of RNN over three conventional optimization algorithms is underlined in terms of MSE, the average time for solving the optimization problem, and the value of the cost function. Full article
(This article belongs to the Special Issue Control Applications and Learning)
Show Figures

Figure 1

16 pages, 3469 KiB  
Article
A PI Controller with a Robust Adaptive Law for a Dielectric Electroactive Polymer Actuator
by Jakub Bernat and Jakub Kolota
Electronics 2021, 10(11), 1326; https://doi.org/10.3390/electronics10111326 - 1 Jun 2021
Cited by 4 | Viewed by 2254
Abstract
Dielectric electroactive polymer actuators are new important transducers in control system applications. The design of a high performance controller is a challenging task for these devices. In this work, a PI controller was studied for a dielectric electroactive polymer actuator. The pole placement [...] Read more.
Dielectric electroactive polymer actuators are new important transducers in control system applications. The design of a high performance controller is a challenging task for these devices. In this work, a PI controller was studied for a dielectric electroactive polymer actuator. The pole placement problem for a closed-loop system with the PI controller was analyzed. The limitations of a PI controller in the pole placement problem are discussed. In this work, the analytic PI controller gain rules were obtained, and therefore extension to adaptive control is possible. To minimize the influence of unmodeled dynamics, the robust adaptive control law is applied. Furthermore, analysis of robust adaptive control was performed in a number of simulations and experiments. Full article
(This article belongs to the Special Issue Control Applications and Learning)
Show Figures

Figure 1

15 pages, 4277 KiB  
Article
Design and Implementation of an Accelerated Error Convergence Criterion for Norm Optimal Iterative Learning Controller
by Saleem Riaz, Hui Lin and Muhammad Pervez Akhter
Electronics 2020, 9(11), 1766; https://doi.org/10.3390/electronics9111766 - 23 Oct 2020
Cited by 17 | Viewed by 2364
Abstract
Designing an optimal iterative learning control is a huge challenge for linear and nonlinear dynamic systems. For such complex systems, standard Norm optimal iterative learning control (NOILC) is an important consideration. This paper presents a novel NOILC error convergence technique for a discrete-time [...] Read more.
Designing an optimal iterative learning control is a huge challenge for linear and nonlinear dynamic systems. For such complex systems, standard Norm optimal iterative learning control (NOILC) is an important consideration. This paper presents a novel NOILC error convergence technique for a discrete-time method. The primary effort of the controller is to converge the error efficiently and quickly in an optimally successful way. A new iterative learning algorithm based on feedback based on reliability against input disruption was proposed in this paper. The illustration of the simulations authenticates the process suggested. The numerical example simulated on MATLAB@2019 and the mollified results affirm the validation of the designed algorithm. Full article
(This article belongs to the Special Issue Control Applications and Learning)
Show Figures

Figure 1

Review

Jump to: Research

35 pages, 4430 KiB  
Review
A Survey on Techniques in the Circular Formation of Multi-Agent Systems
by Hamida Litimein, Zhen-You Huang and Ameer Hamza
Electronics 2021, 10(23), 2959; https://doi.org/10.3390/electronics10232959 - 28 Nov 2021
Cited by 11 | Viewed by 3895
Abstract
Distributed control solutions to the multi-agent systems in terms of coordination, formation, and consensus problems are extensively studied in the literature. The circular formation control of multi-agent systems becomes one of the most challenging and active research topics in distributed cooperative control. The [...] Read more.
Distributed control solutions to the multi-agent systems in terms of coordination, formation, and consensus problems are extensively studied in the literature. The circular formation control of multi-agent systems becomes one of the most challenging and active research topics in distributed cooperative control. The research potential of circular formation control has grown especially in satellite formation and control. The circular formation control aims to drive a group of agents to move on a circular trajectory around a center with spacing adjustment to avoid the collision. This paper covers the fundamental research in consensus and formation control and the latest developments in the applications of formation control especially in circular formation control and stability analysis. Literature related to various control streams to achieve circular formation is discussed. Algebraic graph theory is used as a building block in problem definition, problem formulation, and solutions. A review of bearing, range, and received signal strength measurements with respect to circular formation control is presented. Leader following, behavior-based, artificial potential function, virtual structure, and cyclic pursuit are the methods discussed most in this context. The stabilization of the collective circular motion with the unicycles approach is also discussed. Further results on circular formation, several applications, and future research directions are presented. Full article
(This article belongs to the Special Issue Control Applications and Learning)
Show Figures

Figure 1

Back to TopTop