Neurofuzzy controller design
Dissertant
University
University of Technology
Faculty
-
Department
Department of Control and Systems Engineering
University Country
Iraq
Degree
Ph.D.
Degree Date
1998
English Abstract
As the need for control is extended to systems of increasing complexity which are also often highly nonlinear, the ability to produce a plant model which is adequate overall operating conditions becomes more and more a difficult achieved demanding task, Rule-based fuzzy control, in which the plant model is replaced bv a number of control rules, given by an expert or deduced by observation provides an alternative approach and has been developed significantly in the last decade.
On the other hand, the potential benefits of neural networks extend beyond the high computation rates provided by the massive parallelism to provide a greater degree of robustness, fault tolerance, adaptlvity and generalization.
Seeking for integrating these two approaches brines what is so-called nsurofuzzy system which gives rise to gain the merits of both approaches while avoiding some of their individual drawbacks.
Structural and functional mapping from a fuzzy logic-based algorithm to tire neural network-based approach has been considered with thorough desk procedures for both SISO and MLMO control systems.
In the former iterative input-output gains settings structural neurofuzzy controller has been established based on a furrier element of triangular equation form, a fixed fuzzy production rules learned by back-propagation neural network and a centre of gravity degasification element.
While in the latter the input-output data collected from the, structural font-few been described by their centers only whet have been extracted based on fuzzy number using the mean-tracking clustering algorithm, to he learned by a back-propagation neural network while leaving their widths to be handled by the interpolation feature offered by this network.
To verify the viability of the propped neunrfuzzy controllers a simulation study on different kinds of control systems has been achieved alone with a comparison among many other controllers.
A less involved fuzziness simple architecture, less computational lime and more robust functional neurofuzzy controller has been achieved.
A liquid level control system has been tested as a real-time implementation of the proposed neurofuzzy controllers as well.
Main Subjects
Information Technology and Computer Science
Topics
American Psychological Association (APA)
Ali, Muhammad Mahdi. (1998). Neurofuzzy controller design. (Doctoral dissertations Theses and Dissertations Master). University of Technology, Iraq
https://search.emarefa.net/detail/BIM-306255
Modern Language Association (MLA)
Ali, Muhammad Mahdi. Neurofuzzy controller design. (Doctoral dissertations Theses and Dissertations Master). University of Technology. (1998).
https://search.emarefa.net/detail/BIM-306255
American Medical Association (AMA)
Ali, Muhammad Mahdi. (1998). Neurofuzzy controller design. (Doctoral dissertations Theses and Dissertations Master). University of Technology, Iraq
https://search.emarefa.net/detail/BIM-306255
Language
English
Data Type
Arab Theses
Record ID
BIM-306255