Tuning Of Fuzzy Controller Research Articles

Tuning of fuzzy controller for an open-loop unstable system: a genetic approach

The design, test and evaluation of an optimised fuzzy logic controller (OFLC) is reported in this paper. With the aid of genetic algorithms (GA), the rule-base of an otherwise standard fuzzy logic controller (FLC) is obtained. This is achieved by deriving a tailor-made encoding scheme, initialisation, crossover and mutation of rule table into strings of integers. GA is implemented such that the existing knowledge of the system is utilised to increase the speed of optimisation. The OFLC is successfully applied to control an open-loop unstable system – the ball-and-beam balance system – on a hardware test-bed. A Kalman filter controller (KFC) and a manually tuned fuzzy logic controller (MFLC) are also developed for the test-bed and the performances of the three controllers are compared. The experiment reveals that improved robustness with shorter design cycle can be achieved by integrating GA into an FLC.

Comparison of learning strategies for adaptation of fuzzy controller parameters

For tuning fuzzy controllers, several parameter identification techniques are available, ranging from more robust descent methods to sophisticated optimisation. However, from an application point of view, it is not always clear that numerical sophistication wins over more pragmatic approaches to tuning. Obviously, the data sets play crucial roles in efforts to reach successful tuning. Especially data sets generated from real processes often contain not only noisy data and conflicting subsets, but also the connected problem of non-covering input spaces. In this paper we will compare several parameter identification techniques w.r.t. different data sets. We focus on selections of learning rates and on defining training sequences related to subclasses of parameters.

PROPOSED TUNING TIPS FOR FUZZY CONTROLLERS USING OFFLINE AND ONLINE EXPERIMENTAL AIDS

This paper presents a new real time fuzzy control toolbox. It's associated with online and offline monitoring tools. This is to illustrate the details of the fuzzification, rule base evaluation, and defuzzification processes. A new systematic tuning approach is proposed. The new toolbox supports both PD and PI Fuzzy Control. Real time experimental results of different processes show the power of the toolbox and the proposed fuzzy control tuning method. Real time Robustness experiment shows the need of adaptation if the process change from slow process to a faster one.

A numerical optimization approach for tuning fuzzy logic controllers

This paper develops a method to tune fuzzy controllers using numerical optimization. The main attribute of this approach is that it allows fuzzy logic controllers to be tuned to achieve global performance requirements. Furthermore, this approach allows design constraints to be implemented during the tuning process. The method tunes the controller by parameterizing the membership functions for error, change-in-error, and control output. The resulting parameters form a design vector which is iteratively changed to minimize an objective function. The minimal objective function results in an optimal performance of the system. A spacecraft mounted science payload line-of-sight pointing control is used to demonstrate results.

Simulator for studies of fuzzy control methods

Fuzzy control is of great use in many engineering fields. However, the present design methods of fuzzy control systems depend on trial and error, which limits their usefulness. Therefore, effective and convenient support tools for the study and design of fuzzy control systems are in great demand as well as the establishment of design methods. We have developed a fuzzy control simulator which can implement various fuzzy control methods such as the “direct inference method”, “indirect inference method” and “fuzzy-PID hybrid method”. This paper deals in particular with the function of the “direct inference method” in the simulator. The simulator can implement many kinds of fuzzy inference methods. Using the evaluating functions of the simulator, control performance can be evaluated in real-time or after simulation. Therefore, we can execute the time-consuming and troublesome tasks of tuning fuzzy control parameters efficiently, so that we can design a fuzzy controller suited to a given controlled system.

Tuning of fuzzy PI controllers based on gain/phase margin specifications and ITAE index

In this paper, a new tuning method based on gain margin, phase margin and ITAE index is proposed to determine the parameters (weighting factors) of fuzzy PI controllers with the simplest structure. With the proposed formula, the fuzzy PI controller is tuned appropriately such that it can be applied to different processes modeled approximately as first order plus dead-time dynamics. Numerical and experimental studies show that better performance has been achieved for both set-point change and load disturbance.

Tuning fuzzy logic controllers by genetic algorithms

The performance of a fuzzy logic controller depends on its control rules and membership functions. Hence, it is very important to adjust these parameters to the process to be controlled. A method is presented for tuning fuzzy control rules by genetic algorithms to make the fuzzy logic control systems behave as closely as possible to the operator or expert behavior in a control process. The tuning method fits the membership functions of the fuzzy rules given by the experts with the inference system and the defuzzification strategy selected, obtaining high-performance membership functions by minimizing an error function defined using a set of evaluation input-output data. Experimental results show the method's good performance.

Positioning System with Progressive Wave-Type Ultrasonic Motor under Self-Tuning Fuzzy Control

This paper considers the use of a self-tuning fuzzy controller for a positioning system with a progressive wavetype ultrasonic motor. The system consists of a feedback loop with a conventional controller and a self tuning fuzzy controller. The objective of the self tuning fuzzy controller is to restrain the adverse effect of nonlinear characteristics of the motor and to improve the tracking performance. The self-tuning fuzzy controller is functionally divided into two layers. The fuzzy rules are automatically adjusted by a tuning algorithm so that the tracking error is minimized in the upper layer. In lower layer, the output signal of the self tuning fuzzy controller is obtained by fuzzy reasoning procedure. After the tuning process is completed, the tracking error almost converges to zero, and the ultrasonic motor is no longer controlled by the fixed gain feedback controller but by the self-tuning fuzzy controller. The effectiveness of the proposed self-tuning fuzzy controller is demonstrated by an experiment.

046 The tuning of MIMO fuzzy heuristic controllers: Cheng Ling, T.F. Edgar, pp 231–234

046 The tuning of MIMO fuzzy heuristic controllers: Cheng Ling, T.F. Edgar, pp 231–234

Fuzzy sets and vague environments

In this paper we propose a natural approach to handle imprecise numbers as they arise for example from measurements. Fuzzy sets turn out to be a canonical representation for such imprecise numbers that are induced by taking different tolerance or error bounds into account. Fuzzy sets are induced by scaling factors that describe the magnitude of the imprecision. On the other, the scaling factors can be derived from given fuzzy sets so that we have a correspondence between scaling factors and fuzzy sets. When these concepts are applied, to control problems, the max-min rule is rediscovered as an interpolation technique. Viewing fuzzy control as an interpolation technique in vague environments enables us to validate various concepts for the design and tuning of fuzzy controllers and also suggests new methods based on clear semantics.

The Tuning of MIMO Fuzzy Heuristic Controllers

A MIMO PI controller tuning method has been adapted to tune fuzzy heuristic controllers. The fuzzy heuristic controller gains are calculated by applying the algebraic correlations for controller tuning of first order plus deadtime processes. To date, most fuzzy controller tuning methods reported in the literature apply localized and often ad-hoc modifications of controller actions. The proposed method allows global modification of the controller actions in a systematic manner. By adapting PI tuning methods, the fuzzy heuristic controllers may be tuned based on observations of process responses. Simulations demonstrate that this approach is successful

Application of fuzzy logic in the control of polymerization reactors

Polymer reactors are ideal candidates for the application of fuzzy control. Many polymerization reactions are difficult to model, process measurements are often only available from laboratory analysis at infrequent time intervals and trace impurities can have a marked effect on the reaction. All these factors are manifested in changing polymer properties, which makes control, using a conventional approach, difficult. Over the years, however, process operators have developed the ability to control the reactors under varying conditions. This article outlines how this experience was used in the development of a fuzzy control strategy, and the manner in which feedforward control was incorporated into the design. It also addresses the problem of tuning fuzzy controllers and describes some of the implementation difficulties.

Defuzzification in Fuzzy Controllers

An important subject in fuzzy control theory is tuning of a fuzzy controller. If one wants to tune a fuzzy controller, one can focus on the choice of rules, membership functions, number of input an...