Concept optimization for mechanical product using Genetic Algorithm
Conceptual design is the first step in the overall process of product design. Its intrinsic uncertainty, imprecision, and lack of information lead to the fact that current conceptual design activities in engineering have not been computerized and very few CAD systems are available to support conceptual design. In most of the current intelligent design systems, approach of principle synthesis, such as morphology matrix, bond graphic, or design catalogues, is usually adopted to deal with the concept generation, in which optional concepts are generally combined and enumerated through function analysis. However, as a large number of concepts are generated, it is difficult to evaluate and optimize these design candidates using regular algorithm. It is necessary to develop a new approach or a tool to solve the concept generation. Generally speaking, concept generation is a problem of concept synthesis. In substance, this process of developing design candidate is a combinatorial optimization process, viz., the process of concept generation can be regarded as a solution for a state-place composed of multi-concepts. In this paper, genetic algorithm is utilized as a feasible tool to solve the problem of combinatorial optimizalion in concept generation, in which the encoding method of morphology matrix based on function analysis is applied, and a sequence of optimal concepts are generated through the search and iterative process which is controlled by genetic operators, including selection, crossover, mutation, and reproduction in GA. Several crucial problems on GA are discussed in this paper, such as the calculation of fitness value and the criteria for heredity termination, which have a heavy effect on selection of better concepts. The feasibility and intellectualization of the proposed approach are demonstrated with an engineering case. In this work concept generation is implemented using GA, which can facilitate not only generating several better concepts, but also selecting the best concept. Thus optimal concepts can be conveniently developed and design efficiency can be greatly improved.
Key WordsConceptual Design Genetic Algorithm Optimization Concept Generation Intelligence
Unable to display preview. Download preview PDF.
- Ermer, G., Rosenberg, R. et al., 1993, “Steps toward Integrating Function-based Models and Bond-graphs for Conceptual Design in Engineering,”Automated Modeling for Design, ASME, Vol.47, No. 11, pp. 47–62.Google Scholar
- Huang, H., Zhao, Z. and Guan, L., 2002, “Intelligent Conceptual Design Based on Genetic Algorithm,”Journal of Computer-aided Design & Computer Graphics, Vol. 14, No. 5, pp. 437–441.Google Scholar
- Lim, O. K., Hong, K. S., Lee, H. S. et al., 2004, “Initial Design Domain Reset Method for Genetic Algorithm with Parallel Processing,”KSME International Journal, Vol. 18, No. 7, pp. 1121–1130.Google Scholar
- Park, J. H. and Seo, K. K., 2003, “Approximate Life Cycle Assessment of Product Concepts Using Multiple Regression Analysis and Artificial Neural Networks,”KSME International Journal, Vol. 17, No. 12, pp. 1969–1976.Google Scholar
- Shu, Q. and Hao, B., 2002, “An Automatic Conceptual Design System for Mechanical Products,”China Mechanical Engineering, Vol. 13, No. 19, pp. 1676–1678.Google Scholar
- Yao, Z., Huang, Z. and Shen, G., 1998, “Study on the Structure Catalogues for Conceptual Design of Mechanical Transmission,”China Mechanical Engineering, Vol. 9, No. 6, pp. 53–55.Google Scholar
- Zhou, M. and Sun, S., 1999, Genetic Algorithm: Principle and Application, National Defence Industry Press, Beijing, pp. 45–59.Google Scholar
- Zou, H., Tian, Y., Guo, W. et al., 2003, “Methodology for Conceptual Designof Mechanism System,”J of Shanghai Jiaotong University, Vol. 37. No. 5, pp. 668–673.Google Scholar