Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Bücher
Zeitschriften
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024

Mehr Umsatz mit Top-Kontakten

Am 7. Mai erfahren Sie, wie Vertriebsteams Leadgenerierung, Leadnurturing und Leadstrategien effizient steuern können.
Erweiterte Suche
Anmelden
nach oben

2014 | Buch

Introduction Kapitel lesen Erstes Kapitel lesen

Intelligent Control

A Hybrid Approach Based on Fuzzy Logic, Neural Networks and Genetic Algorithms

verfasst von: Nazmul Siddique

Verlag: Springer International Publishing

Buchreihe : Studies in Computational Intelligence

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten
insite
SUCHEN

Über dieses Buch

Intelligent Control considers non-traditional modelling and control approaches to nonlinear systems. Fuzzy logic, neural networks and evolutionary computing techniques are the main tools used. The book presents a modular switching fuzzy logic controller where a PD-type fuzzy controller is executed first followed by a PI-type fuzzy controller thus improving the performance of the controller compared with a PID-type fuzzy controller. The advantage of the switching-type fuzzy controller is that it uses one rule-base thus minimises the rule-base during execution. A single rule-base is developed by merging the membership functions for change of error of the PD-type controller and sum of error of the PI-type controller. Membership functions are then optimized using evolutionary algorithms. Since the two fuzzy controllers were executed in series, necessary further tuning of the differential and integral scaling factors of the controller is then performed. Neural-network-based tuning for the scaling parameters of the fuzzy controller is then described and finally an evolutionary algorithm is applied to the neurally-tuned-fuzzy controller in which the sigmoidal function shape of the neural network is determined.

The important issue of stability is addressed and the text demonstrates empirically that the developed controller was stable within the operating range. The text concludes with ideas for future research to show the reader the potential for further study in this area.

Intelligent Control will be of interest to researchers from engineering and computer science backgrounds working in the intelligent and adaptive control.

Inhaltsverzeichnis

Frontmatter
Chapter 1. Introduction
Abstract
Traditional model-based control is several hundred years old and has well developed mathematical tools. Despite all these successes, the dissatisfaction with conventional control is growing with increasing complexity of dynamical systems and necessitates the use of more human expertise and knowledge. Intelligent control is a new paradigm that incorporates human knowledge as an important element in control systems design. This chapter introduces the different tools and areas of intelligent control, which is in fact interdisciplinary. Intelligent control combines theories and methods from other disciplines including artificial intelligence, modern adaptive control, learning theory, fuzzy logic and neural networks.
Nazmul Siddique
Chapter 2. Dynamical Systems
Abstract
To apply and verify control strategies, a dynamic model of the system is essential. This chapter presents a general description and characterization of the flexible arm system. The system consists of two main parts; a flexible arm and measuring devices. A numerical method of solution of the governing partial differential equations describing the characteristic behaviour of a flexible arm system incorporating the hub inertia, payload and damping has been presented. Finally a state space model has been derived.
Nazmul Siddique
Chapter 3. Control Systems
Abstract
The basic principle of control is very simple; move the system such that it minimises some error function. A brief theoretical introduction to control system is presented for understanding the controller design in this chapter. Different control schemes such as open-loop and closed-loop control strategies are discussed. Application of open-loop control strategy is limited. The problems of closed-loop control strategies are associated with measurement of the control variables and based on the measurement using suitable sensor mechanism, collocated an non-collocated control approaches have been suggested depending on the accuracy of the available models.
Nazmul Siddique
Chapter 4. Mathematics of Fuzzy Control
Abstract
Fuzzy logic is one of the main constituents of intelligent control developed by Lotfi Zadeh in 1960s. This chapter introduces fuzzy sets, fuzzy logic and their representation using membership functions. Fuzzy models, rule-base, fuzzification, inferencing, defuzzification are the approaches to fuzzy modelling and control. The chapter also discusses membership function shapes, fuzzy models such as Mamdani, Takagi-Sugeno and Tsukamoto models, rule-base construction and finally different defuzzification methods and their important role in designing efficient fuzzy system and controller.
Nazmul Siddique
Chapter 5. Fuzzy Control
Abstract
PD-like and PI-like fuzzy logic controllers (FLC) have the same characteristics as the traditional PD and PI-type controllers. That is, PD-like FLC exhibits smaller overshoot, fast rise time and small settling time but shows significant steady state error. Whereas PI-like FLC improves the steady state error but exhibits penalised rise time, large overshoot and excessive oscillation. This chapter investigates different types of fuzzy PD and PI controllers and proposes a switching PD-PI-like FLC that shows improved performance and demonstrates advantages over the PD, PI and PID like FLCs. Firstly, it improves the steady state error and reduces the rise time and settling time. Secondly, it reduces rule-base from n3 to only n2 . This chapter also investigates the integral windup action, which is an important issue in designing FLC with integral element.
Nazmul Siddique
Chapter 6. Evolutionary-Fuzzy Control
Abstract
Construction of membership functions (MF) and rule-base is one of the most important considerations in designing fuzzy logic controllers (FLC). With an increasing number of inputs and linguistic variables, the possible number of rules for the system increases exponentially, which makes it difficult for experts to define a complete set of rules and associated MFs. This chapter investigates the use of genetic algorithm (GA) for an automated way of designing FLC. The proposed GA uses dynamic crossover and mutation probability. The evaluation of GA on a real system imposes restriction on the size of the population and also the number of generations.
Nazmul Siddique
Chapter 7. Neuro-Fuzzy Control
Abstract
Performance improvement of fuzzy logic controllers (FLC) can be achieved by adjusting the membership functions (MF). Neuro-fuzzy approaches are mostly used in such adjustment procedure, which involves several parameters of the MFs to be adjusted. In many cases, tuning the scaling factors gives the same performance as with MFs adjustment. Secondly, tuning the scaling factors is a simpler task than adjusting the membership functions. This chapter develops a mechanism of tuning the scaling factors of the PD-PI-like FLC by using a single-neuron network. Experiments show that non-linearity can be sufficiently approximated by determining the shape of the sigmoidal function.
Nazmul Siddique
Chapter 8. Evolutionary-Neuro-Fuzzy Control
Abstract
It has been demonstrated that learning the shape of sigmoidal function can improve performance of neuro-fuzzy controller. Backpropagation learning algorithm does not include the parameter of the sigmoidal function shape. This chapter proposes the use of genetic algorithm to learn the weights, biases and shape of the sigmoidal function of the neural network simultaneously. The performance of the system using a neural network with a linear activation function seems to be better than neural network with a non-linear activation function.
Nazmul Siddique
Chapter 9. Stability Analysis of Intelligent Controllers
Abstract
Consistent analysis of fuzzy logic controllers (FLC) has been a painful part of fuzzy systems theory for a long time. FLC was accused of being unreliable approximate engineering approach, which uses experience, intuition and rules of thumb instead of consistent firm analytical theory. This chapter investigates different approaches to stability analysis of FLCs. The study reveals that the system trajectory method can be applied to investigate the stability of FLC. The chapter demonstrates the stability of the PD-PI-like FLC, GA-based FLC and Neuro-FLC and GA-based Neuro-FLC.
Nazmul Siddique
Chapter 10. Future Work
Abstract
Fuzzy logic controllers (FLC) have been extensively applied to many engineering and industrial problems. There are still many problems associated with the construction and processing membership functions, rule-base and defuzzification. This chapter firstly highlights the salient features of the PD-PI-like FLC in combination with neural networks and genetic algorithms and secondly provides few future research directions that can be associated with the current research.
Nazmul Siddique
Backmatter
Metadaten
Titel
Intelligent Control
verfasst von
Nazmul Siddique
Copyright-Jahr
2014
Electronic ISBN
978-3-319-02135-5
Print ISBN
978-3-319-02134-8
DOI
https://doi.org/10.1007/978-3-319-02135-5

Neuer Inhalt

    Bildnachweise