An Enhanced Genetic Algorithm for Optimizing and Controlling Dynamic Systems at Real-Time

Awad, Hamdi  A.

doi:10.21608/mjeer.2010.66197

	An Enhanced Genetic Algorithm for Optimizing and Controlling Dynamic Systems at Real-Time
Menoufia Journal of Electronic Engineering Research
Article 3, Volume 20, Issue 1, January 2010, Pages 25-44
Document Type: Original Article
DOI: 10.21608/mjeer.2010.66197
Author
Hamdi A. Awad
Dept. of Industrial Electronics and Control Eng., Faculty of Electronic Engineering, Menouf, 32952, Minufiya University, Egypt
Abstract
Genetic Algorithm (GA) has superiority over the classical optimization algorithms in finding the optimal solution in multi-parameter search space. Despite this superiority, it suffers from using an arbitrary selection of the binary length of each gene string that represents a single parameter in a chromosome (solution). The length of each gene depends not only on the lower and upper limits of the parameter to be optimized, but also on the resolution required. If the resolution is too coarse, the GA may never be able to find optima simply. This paper introduces an enhanced version of GAs (EGA) that uses a set of real parameters’ values to represent a chromosome instead of a set of binary codes. It also proposes a control scheme based on the EGA for controlling dynamic processes at real-time. The proposed scheme can control a complex industrial process with time constant less than 2 ms.
Keywords
Recurrent neural networks; GA; DC machines; Takagi-Sugeno Models

References
[1] Daihee P, Abraham K, Gideon, L., (1994) Genetic-Based New Fuzzy Reasoning Models with Application to Fuzzy Control. IEEE Transactions Systems, Man and Cybernetics, 24 (1), 39-47. DOI: 10.1109/21.259684 [2] Linkens DA, Nyongesa HO, (1995) Genetic Algorithms for Fuzzy Control. IEE Proc. Control Theory and Applications, 142 (3), 161-176. DOI: 10.1049/ip-cta:19951766 [3] Poonsawat S, Kulworawanichpong T, (2008) Speed Regulation of a Small BLDC Motor using Genetic-based Proportional Control, Proceedings of World Academy of Science Engineering and Technology, ISSN 1307-6884, 30, 849-854. [4] Meng JE, Jun L, Jianya L (2000) Fuzzy Neural Networks-Based Quality Prediction System for Sintering Process, IEEE Transactions Fuzzy Systems, 8, (3), 314-324. DOI: 10.1109/91.855919 [5] Saleh RA (2001) Application of Artificial Intelligent Techniques to the Design of Improved Stabiliser for Superconducting Generators, Dissertation, Cardiff University. [6] Allaoua B, Abderrahmani A, Gasbaoui B, Nasri, A (2008) The Efficiency of Particle Swarm Optimization Applied on Fuzzy Logic DC Motor Speed Control, Serbian Journal of Electrical Engineering, (5), 247-262. [7] Pham DT, Liu HX, (1995) Neural Network for Identification, Prediction and Control, British Library, Springer-Verlag, London. ISBN 3-540-19959-4. [8] Khalifa YA (1997) Evolutionary Methods for the Design of Electronic Circuits and Systems. Dissertation, Cardiff University. [9] Song YH, and Chou CV (1997) Advanced Engineered Conditioning Genetic Algorithm Approach to Power Economic Dispatch. IEE Proc., Part-C, 144 (3), 285-292. DOI: 10.1049/ip-gtd:19970944 [10] Wen FS, Chang CS (1997) Probabilistic Approach for Fault Section Estimation in Power Systems based on A refined Genetic Algorithm. IEE Proc., Pt. C, (144), 160-168. DOI (Automatica): 10.1590/S0103-17592004000200010 [11] Juang CF (2002) A TS-Type Recurrent Fuzzy Network for Dynamic Systems Processing by Network and Genetic Algorithms. IEEE Trans. Fuzzy Systems, (10), 155-170. [12] Porter L, Passino K (1998) Genetic Adaptive and Supervisory Control. Int. J. Control and System, (2), 1-41. [13] Juang C F, Lin CT (1998) An Online Self- Constructing Neural Fuzzy Inference Network and its Applications, IEEE Trans. Fuzzy Systems. (6), 12-32. [14] Awad, HA (2001) Fuzzy Neural Networks for Modeling and Controlling Dynamic Systems. Dissertation, Cardiff University.
Statistics Article View: 116