Intelligent Control Approaches for Modeling and Control of Complex Systems (original) (raw)
Related papers
A New Approach for Controlling a Trajectory Tracking Using Intelligent Methods
Journal of Electrical Engineering & Technology, 2019
This study aimed to propose and compare two control methods to guide a mobile robot during trajectory tracking. The conventional proportional-integral-derivative (PID) control is widely used in several non-linear systems control area for its simplicity and robustness. But it is difficult to adjust the parameters of the PID controller to satisfy the requirements of the control systems. In this article, we present the neuro-PI + D control and fuzzy-neuro-PI + D control. We use those techniques of artificial intelligence to guarantee autonomy and intelligence for the path following behavior. The robot under consideration is a four-wheeled system and is represented by a kinematic model. Matlab/Simulink simulation results demonstrate that the fuzzy-neuro-PI + D method has a great potential for navigation issue.
A Comprehensive Review on Intelligence Control for Complex System
Control system intellectualization issues are observed. The need for intellectualization of a diverse variety of systems and control approaches is supported. The hierarchy of intellectual control levels is examined, and various artificial intelligence methods are compared. Intelligence control for complex systems involves using advanced algorithms and techniques, such as artificial intelligence and machine learning, to effectively manage and manipulate complex systems. This includes creating models and simulations to understand the system's behavior, sensing and acquiring real-time data, preprocessing and analyzing the data, making decisions based on the analyzed data and system models, adapting control strategies in real-time, facilitating human-machine interaction, monitoring performance, and optimizing control strategies. The goal is to improve efficiency, safety, reliability, and overall performance of complex systems in various domains.
Computational Intelligence in Control
2003
This book covers the recent applications of computational intelligence techniques for modelling, control and automation. The application of these techniques has been found useful in problems when the process is either difficult to model or difficult to solve by conventional methods. There are numerous practical applications of computational intelligence techniques in modelling, control, automation, prediction, image processing and data mining. Research and development work in the area of computational intelligence is growing rapidly due to the many successful applications of these new techniques in very diverse problems. "Computational Intelligence" covers many fields such as neural networks, (adaptive) fuzzy logic, evolutionary computing, and their hybrids and derivatives. Many industries have benefited from adopting this technology. The increased number of patents and diverse range of products developed using computational intelligence methods is evidence of this fact. These techniques have attracted increasing attention in recent years for solving many complex problems. They are inspired by nature, biology, statistical techniques, physics and neuroscience. They have been successfully applied in solving many complex problems where traditional problem-solving methods have failed. These modern techniques are taking firm steps as robust problem-solving mechanisms. This volume aims to be a repository for the current and cutting-edge applications of computational intelligent techniques in modelling control and automation, an area with great demand in the market nowadays. With roots in modelling, automation, identification and control, computational intelligence techniques provide an interdisciplinary area that is concerned with learning and adaptation of solutions for complex problems. This instantiated an enormous amount of research, searching for learning methods that are capable of controlling novel and non-trivial systems in different industries. This book consists of open-solicited and invited papers written by leading researchers in the field of computational intelligence. All full papers have been peer review by at least two recognised reviewers. Our goal is to provide a book TLFeBOOK viii that covers the foundation as well as the practical side of the computational intelligence. The book consists of 17 chapters in the fields of self-learning and adaptive control, robotics and manufacturing, machine learning, evolutionary optimisation, information retrieval, fuzzy logic, Bayesian systems, neural networks and hybrid evolutionary computing. This book will be highly useful to postgraduate students, researchers, doctoral students, instructors, and partitioners of computational intelligence techniques, industrial engineers, computer scientists and mathematicians with interest in modelling and control. We would like to thank the senior and assistant editors of Idea Group Publishing for their professional and technical assistance during the preparation of this book. We are grateful to the unknown reviewers for the book proposal for their review and approval of the book proposal. Our special thanks goes to Michele Rossi and Mehdi Khosrowpour for their assistance and their valuable advise in finalizing this book. We would like to acknowledge the assistance of all involved in the collation and review process of the book, without whose support and encouragement this book could not have been successfully completed. We wish to thank all the authors for their insights and excellent contributions to this book. We would like also to thank our families for their understanding and support throughout this book project.
Fuzzy System to Control the Movement of a Wheeled Mobile Robot
Studies in Computational Intelligence, 2010
The series Studies in Computational Intelligence (SCI) publishes new developments and advances in the various areas of computational intelligence -quickly and with a high quality. The intent is to cover the theory, applications, and design methods of computational intelligence, as embedded in the fields of engineering, computer science, physics and life science, as well as the methodologies behind them. The series contains monographs, lecture notes and edited volumes in com putational intelligence spanning the areas of neural networks, connectionist systems, genetic algorithms, evolutionary computation, artificial intelligence, cellular automata, self-organizing systems, soft computing, fuzzy systems and hybrid intelligent systems. Critical to both contributors and readers are the short publication time and world-wide distribution -this permits a rapid and broad dissemina tion of research results.
From Nonlinear to Fuzzy Approaches in Trajectory Tracking Control of Wheeled Mobile Robots
Asian Journal of Control, 2012
In this paper, two knowledge based controllers are proposed to overcome the difficulties of a computed torque nonlinear controller (NC) in perfect trajectory tracking of nonholonomic wheeled mobile robots (WMRs). First, the effects of different dynamic models developed in angular and Cartesian coordinate systems are fully examined on the persistent excitation condition and consequently on the trajectory tracking performance of WMRs. Using the dynamic model coordinated in the Cartesian frame as the base of the NC results in perfect compensation of large position off-tracks and unbiased estimation of the plant's unknown parameters. However, using the WMR's dynamic model with rotation angles of driving wheels as the base of nonlinear and fuzzy controllers leads to accurate orientation tracking. Through replacing the proportional and differential terms of the NC by fuzzy functions, a fuzzy nonlinear controller (FNC) is generated. Due to the complicated dynamics of the WMR in which the center of mass does not coincide with the center of rotation, the expert knowledge of fuzzy controllers is extracted considering the rotation angles and rates of driving wheels as input variables. Fuzzy tuning of the NC results in a superior tracking performance against measurement noises, though the control torques are decreased and smoothed significantly. Second, a complete fuzzy controller (FC) is generated to make perfect tracking of the WMR's position and orientation. The local stability analysis of fuzzy controllers is examined considering the corresponding analytical structures as nonlinear controllers. The superior performances of the proposed fuzzy controllers compared to those of the NCs are evaluated through simulations. in Persian. His main research interests are: theory of computational intelligence, learning automata, adaptive filtering and their applications in control, power systems, image processing, pattern recognition, and communications, and other areas of interests are: theory of rough set and knowledge discovery.
From Model-Based Strategies to Intelligent Control Systems
This paper presents the evolution of control systems and trends in the field of integrated computer, communication and cognitive sciences for control applications. There have been selected and presented the most efficient control strategies used in complex process control, as well as the limitations of model-based approaches in cases that imply complex, non-linear and uncertain process models. In this context, the paper presents some trends in robust identification and design of adaptive control systems with a high level of robustness. Concepts for autonomous control of complex systems by the integration of intelligent methodologies are analyzed. Some aspects of hybrid intelligent control are considered and new directions of research towards creating a new gener- ation of control systems are presented. The paper also includes a review of the evolution of computer controlled applications and a new paradigm - C4 - is analyzed from concept to application. Therefore, the transition from...
Plenary lecture I: from model-based strategies to intelligent control systems
2008
The paper presents the evolution of control systems and trends in the field of integrated computer, communication and cognitive sciences for control applications. There are selected and presented the most efficient control strategies used in complex process control, as well as the limitations of model-based approaches in cases implying complex, non-linear and uncertain process models. In this context are presented some trends in robust identification and design of adaptive control systems with high level of robustness. There are analyzed the concepts for autonomous control of complex systems by integrating intelligent methodologies. Some aspects of hybrid intelligent control are considered and are also presented some new directions of research towards creating a new generation of control systems. The paper includes also a presentation of the evolution of computer controlled applications and a new paradigm - C4 - is analyzed from concept to application. Therefore, it is illustrated t...
Nowadays, modern complex systems of any interdisciplinary nature can hardly be analyzed and/or modeled without comprehensive usage of system theoretic approach. The complexity and uncertainty of the nature of modern systems, and the heterogeneity of related information, require a complex approach for their study, based on systems theory and systems analysis and consisting of information and expert knowledge management, initial pre-processing, modeling, simulation, and decision making support. As the complexity of systems increases, system theoretic methods become more crucial. Often they provide the only effective tools of obtaining the information about the elements in a system, connections between those elements, and the means for getting the adequate representation of system in a whole. The variety of complex systems can be described by deterministic or stochastic differential equations, statistical mechanics equations, neural network models, cellular automata, finite state machines, multi-agent systems, etc. Most of the complex real world objects are modeled as dynamic systems enriched by artificial intelligence resources. Equipped with artificial intelligence techniques, these models offer a wide variety of advantages such as coping with incomplete information and uncertainty, predicting system's behavior, reasoning on qualitative level, knowledge representation and modeling, where computer simulations and information systems play an important and active role, and facilitate the process of decision making.