Advertisement

Adaptive Restricted Tournament Selection for the identification of multiple sub-optima in a multi-modal function

  • R. Roy
  • I. C. Parmee
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1143)

Abstract

Adaptive Restricted Tournament Selection (ARTS) is a multi-modal genetic algorithm technique. The technique identifies multiple “good” solutions from a multi-modal fitness landscape. ARTS uses a shared near neighbour clustering technique to define the closest point from any individual in a generation. The technique is an improvement over the Restricted Tournament Selection (RTS). ARTS differs from RTS by the fact that the former requires no prior knowledge about the modality of the fitness landscape to distribute the final population on different peaks. This paper describes the ARTS technique and also compares its performance with other recent multi-modal function optimisation techniques. ARTS has been applied to a multi dimensional turbine blade cooling system design problem. The results are presented and discussed.

Key words

multi-modal genetic algorithms evolutionary computing optimisation genetic algorithms ARTS tournament selection real life problem optimisation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. I. C. Parmee, M. Johnson and S. Burt, Techniques to Aid Global Search in Engineering Design, Proceedings of the Seventh International Conf. on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, May 31–June 3, Austin, Texas, 377–385, 1994.Google Scholar
  2. I. C. Parmee and M. J. Denham, The Integration of Adaptive Search Techniques with Current Engineering Design, Proceedings of ACEDC'94, 21–22 September, Plymouth (UK), 1–13, 1994.Google Scholar
  3. D. E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley Publishing Comp., Inc., 1989.Google Scholar
  4. R. Roy, I. C. Parmee and G. Purchase, Integrating the Genetic Algorithms with the Preliminary Design of Gas Turbine Blade Cooling Systems, Proc. of ACEDC'96 Conf., 26–28 March, Plymouth (UK), pp. 228–235, 1996a.Google Scholar
  5. R. Roy, I. C. Parmee and G. Purchase, Qualitative Evaluation of Engineering Designs using Fuzzy Logic, Proc. of the ASME DETC-Design Automation Conference, 18–22 August, Irvine, CA, 1996b.Google Scholar
  6. R. Roy, I. C. Parmee and G. Purchase, Sensitivity Analysis of Engineering Designs using Taguchi's Methodology, Proc. of the ASME DETC-Design Automation Conference, 18–22 August, Irvine, CA, 1996c.Google Scholar
  7. R. Roy and I. C. Parmee, Adaptive Restricted Tournament Selection for Multi-modal Function Optimisation, Plymouth Engineering Design Centre Internal Report No.: PEDC-03-95, Univ. of Plymouth (UK), May 1995.Google Scholar
  8. G. Harik, Finding Multiple Solutions In Problems of bounded Difficulty, IlliGAL Report No. 94002, Urbana: Univ. of Illinois, Illinois Genetic Algorithms Laboratory, May 1994.Google Scholar
  9. S. W. Mahfoud, Crowding and Preselection Revisited, Parallel Problem Solving from Nature, 2, Manner, R. and Manderick, B. (Eds.), Elsevier Science Pub. B.V., 27–36, 1992.Google Scholar
  10. S. W. Mahfoud, Niching Methods for Genetic Algorithms, PhD Thesis (IlliGAL Report No.: 95001), Urbana: University of Illinois, Illinois Genetic Algorithms Laboratory, May 1995.Google Scholar
  11. K. A. De Jong, An Analysis of the Behavior of a Class of Genetic Adaptive Systems, Ph.D. Dissertation, Univ. of Michigan, Dissertation Abstracts International, 36 (10), 5140B (Univ. Microfilms No. 76-9381), 1975.Google Scholar
  12. S. W. Mahfoud, Crossover Interactions Among Niches, Proc. of the First IEEE Conference on Evolutionary Computation, June 27–29, Orlando, Florida, 188–193, 1994.Google Scholar
  13. D. Beasley, D. R. Bull and R. R. Martin, A Sequential Niche Technique for Multi-modal Function Optimization, Evolutionary Computation, MIT Press, vol. 1, no. 2, 101–125, 1993.Google Scholar
  14. I. C. Parmee, Maintenance of Search Diversity for Effective Design Space Decomposition using Cluster-Oriented Genetic Algorithms (COGAs) and Multi-Agent Strategies (GAANT), Proc. of the ACEDC'96 Conf, 26–28 March, Plymouth (UK), pp. 128–138, 1996.Google Scholar
  15. G. Harik, Finding Multi-modal Solutions Using Restricted Tournament Selection, Proc. of 6th ICGA Conf., 15–20 July, Pittsburgh, 1995.Google Scholar
  16. G. Syswerda, A Study of Reproduction in Generational and Steady-State Genetic Algorithms, Foundations of Gas, G. J. E. Rawlins (Ed.), Morgan Kaufmann Pub., 94–101, 1991.Google Scholar
  17. R. A. Jarvis and E. A. Patrick, Clustering using a Similarity Measure Based on Shared Near Neighbors, IEEE Transactions on Computers, vol. 22, no. 11, 1973.Google Scholar
  18. R. Roy, I. C. Parmee and G. Purchase, Qualitative Evaluation of Engineering Design using Fuzzy Logic, Plymouth Engineering Design Centre Internal Report No.: PEDC-04-95, Univ. of Plymouth (UK), May 1995.Google Scholar
  19. D. Dasgupta and D. R. Mcgregor, A Structured Genetic Algorithms: the Model and First Results, Research report IKBS-2-91, University of Strathclyde (UK), 1991.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • R. Roy
    • 1
  • I. C. Parmee
    • 1
  1. 1.Plymouth Engineering Design Centre, Charles Cross CentreUniversity of PlymouthPlymouthUK

Personalised recommendations