UDC 004.4'2, DOI: 10.2298/csis0902141E

The Adaptive Fuzzy Designed PID Controller using Wavelet Network

Ibrahiem M. M. El Emary1, Walid Emar2 and Musbah J. Aqel3

  1. King Abdulaziz University
    P.O. Box 18388, Jeddah, King Saudi Arabia
    Omary57@hotmail.com
  2. Faculty of Engineering, Al Isra University
    Amman, Jordan
    Walidemar23@yahoo.com
  3. Faculty of Engineering, Applied Science University
    Amman, Jordan
    musbahaqel@yahoo.com

Abstract

During the past several years, fuzzy control has emerged as one of the most active and fruitful areas of research in the applications of the fuzzy set theory, especially in the realm of the industrial processes, which do not lend themselves to be controlled by conventional methods because of a lack of quantitative data regarding the input-output relations i.e., accurate mathematical models. The fuzzy logic controller based on wavelet network provides a means of converting a linguistic control strategy based on expert knowledge into an automatic strategy. In the available literature one can find scores of papers on fuzzy logic based controllers or fuzzy adaptation of PID controllers [3]. However, relatively less number of papers is found on fuzzy adaptive control, which is not surprising since fuzzy adaptive control is relatively new tool in control engineering. This paper presents a recent development of PID controllers. The proposed controller design aims to overcome the drawbacks of classical PID controller, such as: integrator windup due to the saturation in the actuator and the slow response to reject disturbances. In this paper fuzzy adaptive PID controller with wavelet network is discussed in subsequent sections with simulations. The Neural Wavelet Network (NWN) structure is implemented and an example of a second order system is carried out to verify this implementation. Also, in this paper, it is proposed that the controller is tuned using Adaptive fuzzy controller serving as a stochastic global search method that emulates the process of natural evolution. It is shown that Adaptive fuzzy controller is capable of locating high performance areas in complex domains without experiencing the difficulties associated with high dimensionality or false optima as it may occur with gradient decent techniques. From the output results, it was shown that it gave fast convergence for the nonparametric function under consideration in comparison with conventional Neural Wavelet Network (NWN). The proposed control design methodology was tested on a numerical example via simulation. The simulation work was carried out using MATLAB/SIMULINK and SIMPLORER 6 environment. The obtained results affirm the potential of the proposed control methodology to add self-autonomy to the system behaviour.

Key words

Wavelet network, fuzzy logic, PID controller

Digital Object Identifier (DOI)

https://doi.org/10.2298/csis0902141E

Publication information

Volume 6, Issue 2 (December 2009)
Year of Publication: 2009
ISSN: 1820-0214 (Print) 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Emary, I. M. M. E., Emar, W., Aqel, M. J.: The Adaptive Fuzzy Designed PID Controller using Wavelet Network. Computer Science and Information Systems, Vol. 6, No. 2, 141-163. (2009)