Fuzzy Control System Review

Computers in Industry, 2003

A way to automatically generate fuzzy controllers (FCs) that are optimized according to a merit figure is presented in this article. To achieve this task, a procedure based on hierarchical genetic algorithms (HGA) was developed. This procedure and the manner in which fuzzy controllers are codified into chromosomes is described. Resorting to this tool, several fuzzy controllers were constructed. The best three solutions obtained during simulation were selected for testing using an experimental prototype, which consists of an induction motor of variable load. These preliminary results are also included in the report. Based on these results, it is concluded that hierarchical genetic algorithms, though not the only, is a suitable artificial intelligence technique to face the problem of setting a fuzzy controller in a control loop without previous experience in controlling the plant. This is of help in many situations at industrial environments.

All control systems suffer from problems related to undesirable overshoot, longer settling times and vibrations while going form one state to another state. Most of relevant techniques had been in the form of suggesting modification and improvement in the instrumentation or interfacing part of the control system and the results reported, remain suffering from shortcomings related to hardware parameter dependence and maintenance and operational complexities. Present study was based on a software approach which was focusing on an algorithmic approach for programming a PIC16F877A microcontroller, for eliminating altogether the parametric dependence issues while adding the benefits of easier modification to suit a given control system to changing operational conditions. Said approach was first simulated using MATLAB/SIMULINK using the techniques of Proportional Derivative Fuzzy Logic Controller (PD-FLC) whose membership function, fuzzy logic rules and scaling gains were optimized by the genetic algorithm technique. Simulated results were verified by programming the PIC16F877A microcontroller with the algorithm and using it on a temperature control system where a fan was regulated in response to variations in the ambient system temperature. Resulting tabulated performance indices showed a considerable improvement in rising and settling time besides reducing overshoot and steady state error.

International Standard Book Number-10: 0-8493-3747-X (Hardcover) International Standard Book Number-13: 978-0-8493-3747-5 (Hardcover) Library of Congress Card Number 2005054270

Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406)

In this paper, FCDT (Fuzzy Controllers Development Tool) is presented. FCDT is a software tool that provides a graphical environment to develop and test fuzzy controllers. Complete fuzzy controllers can be defined, enhanced manually and tested on target systems. FCDT implements a neural network based algorithm that can be used to enhance automatically the fuzzy controllers and an evolutionary algorithm that allows the design of the fuzzy rule base and the number and shape of membership functions for the output variables automatically. FCDT, documentation, examples and its source code is made available in the hope that it will be useful to the research community.

Classical control theory is based on the mathematical models that describe the physical plant under consideration. The essence of fuzzy control is to build a model of human expert who is capable of controlling the plant without thinking in terms of mathematical model. The transformation of expert's knowledge in terms of control rules to fuzzy frame work has not been formalized and arbitrary choices concerning, for example, the shape of membership functions have to be made.

Design of fuzzy controllers has been always a job built on past experience and knowledge of fuzzy control and systems behavior. Unlike that fashion this research introduced a new methodology of designing fuzzy controllers using genetic algorithms. The design employs Sugeno type fuzzy controllers as the parameters can be manipulated using GA. Single and two inputs fuzzy controllers are used. This research presented a solution of first, second, and third order systems, using the absolute average error as a fitness function, the genetic algorithm manipulate all parameters of the fuzzy controller to find the optimum solution. The simulation model used Matlab GA toolbox for finding the optimal solution, the fitness function took a different shape than the usual form, the new shape is introduced using a short program that is capable of generating the whole system, then calculating its output, error and finally the average error which is used as a fitness value to finally design the fuzzy ...

International Journal of Advancements in Computing Technology, 2011

In this work we consider the design of neural network and Takagi Sugeno fuzzy logic controller, TSFLC, with Multi-Obejctive Genetic Algorithm, MOGA. For the neural network, the MOGA has to minimize three objectives, the cumulated error, the number of neurons in the hidden layer and the number and type of inputs to the network. In the case of the TS FLC, the objectives are the cumulated error and the parameters of the rules consequence. Both algorithms are applied for the control of temperature system.

Many non-linear, inherently unstable systems exist whose control using conventional methods is both difficult to design and unsatisfactory in implementation. Fuzzy Logic Controllers are a class of non-linear controllers that make use of human expert knowledge and an implicit imprecision to apply control to such systems. The performance of Fuzzy Logic Controller depends on its control rules and membership functions. Hence it is very important to adjust these parameters. The incorporation of genetic algorithm into a fuzzy design process adds an 'intelligent' dimension to the fuzzy controller enabling it to create and modify its rules. Genetic algorithms give the possibility of adjusting membership functions down to the level of individual rules. In this paper, the idea of model generation and optimization is explored. Fuzzy process models will be generated and parameters of fuzzy logic controller such as centre of membership function and weight of the rules are optimized using the power of genetic algorithms. The Inverted pendulum system is used as a test system for this approach.

Classical control theory is based on the mathematical models of the physical plants. Getting an accurate model of the plant is a basic problem in designing controllers in process industries. The problems of classical control schemes can be solved by incorporating the artificial intelligence. The aim of this paper is to present a versatile technique, Fuzzy Logic which is simple and easy to understand. But the Fuzzy frame work is not formalized. An expert's knowledge is needed for the accurate tuning of Fuzzy Logic controller. This paper presents a method for tuning Fuzzy Logic controller. Tuning can be effectively done by using Neural network. In this research an attempt has been made to design a Fuzzy Logic controller for a coupled tank system, using neural network as a tuning tool. The simulation and real time responses shows the effectiveness of the proposed scheme..

1993

X Congreso Español sobre Tecnologías y Lógica Fuzzy ESTYLF'00, 2000

In this paper, an analysis of the role of fuzzy logic controllers is carried out. Its interpretation and the conditions for successful implementation in several control structures, jointly with their advantages and drawbacks with relation to other advanced control approaches are discussed.

Computers in Industry, 2011

Diagnostyka

The paper represents laboratory bench to analyse a system of automated control with a fuzzy controller. The laboratory bench consists of a thermal object, and software and hardware complex involving logic controller VIPA System 200 V as well as HMI / SCADA system Zenon Supervisor 7.0. The thermal object is described with the help of the second-order differential equation using "current value within the power converter of electric heater-air temperature inside a thermal object" control channel. Coefficients of the differential equation depend upon location of a dampener and upon rotation frequency of a centrifugal fan. Control error (ie deviation between the specified temperature value within the thermal object and its current value), and derivative of the error, represented in the form of linguistic variables involving five triangular terms and two trapezoidal (extreme) ones have been used as the input values of the fuzzy controller. Output value of the fuzzy controller is the electric power supplied to the electric heater and assuming seven specified values. Selection of the specific value of electric power depends upon knowledge base being a finite set of rules of fuzzy sets falling into line with the applied linguistic variables. To implement such a system of automated control with a fuzzy controller, original software has been developed making it possible to analyze a process of thermal object heating with the use of human-computer interface. Interaction algorithm of certain program elements has been described. Experimental results, concerning the thermal object transfer from different initial conditions to terminal ones, have been demonstrated. A dependence of mean-square error of the controlled value upon the control period has been demonstrated.

Information Sciences, 1985

This paper reviews the studies on fuzzy control by referring to most of the papers ever written on fuzzy control. As an introduction, the paper picks up key points in applying fuzzy control and shows very recent results in industrial applications. The paper also points out some interesting and important problems to be solved.

International Conference on Electrical and Electronics Engineering, 2017

1 blank line using 9-point font with single spacing There are many different design parameters such as membership functions, scaling factors, inference and defuzzification methods in the structures of fuzzy logic controllers. Most of the time, it is difficult to determine the parameters accurately even with the help of experts. For this purpose, genetic algorithm one of the heuristic optimization techniques is used to facilitate the design of optimal fuzzy logic controller in this study. Fuzzy logic controllers used in the studies are designed with entirely user-defined software instead of toolboxes. Performances of the designed controllers have been analyzed through simulation studies performed on the permanent magnet synchronous motor. Results obtained from the simulation studies have showed that fuzzy logic controllers optimized based on ITAE performance indice have better performance.