Improving multi-objective genetic algorithms with adaptive design of experiments and online metamodeling Export

@article{citeulike:5973132, abstract = {Applications of multi-objective genetic algorithms (MOGAs) in engineering optimization problems often require numerous function calls. One way to reduce the number of function calls is to use an approximation in lieu of function calls. An approximation involves two steps: design of experiments (DOE) and metamodeling. This paper presents a new approach where both DOE and metamodeling are integrated with a MOGA. In particular, the DOE method reduces the number of generations in a MOGA, while the metamodeling reduces the number of function calls in each generation. In the present approach, the DOE locates a subset of design points that is estimated to better sample the design space, while the metamodeling assists in estimating the fitness of design points. Several numerical and engineering examples are used to demonstrate the applicability of this new approach. The results from these examples show that the proposed improved approach requires significantly fewer function calls and obtains similar solutions compared to a conventional MOGA and a recently developed metamodeling-assisted MOGA.}, author = {Li, G. and Li, M. and Azarm, S. and Al Hashimi, S. and Al Ameri, T. and Al Qasas, N.}, citeulike-article-id = {5973132}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/s00158-008-0251-6}, citeulike-linkout-1 = {http://www.springerlink.com/content/c43145t064534p7l}, day = {1}, doi = {10.1007/s00158-008-0251-6}, journal = {Structural and Multidisciplinary Optimization}, keywords = {design\_of\_experiments, evolutionary\_algorithm, incremental, kriging, metamodel, multiobjective, optimization, pareto\_front, uncertainty}, month = {February}, number = {5}, pages = {447--461}, posted-at = {2009-10-20 07:44:57}, priority = {2}, title = {Improving multi-objective genetic algorithms with adaptive design of experiments and online metamodeling}, url = {http://dx.doi.org/10.1007/s00158-008-0251-6}, volume = {37}, year = {2009} }

TY - JOUR ID - citeulike:5973132 L3 - citeulike-article-id:5973132 N2 - Applications of multi-objective genetic algorithms (MOGAs) in engineering optimization problems often require numerous function calls. One way to reduce the number of function calls is to use an approximation in lieu of function calls. An approximation involves two steps: design of experiments (DOE) and metamodeling. This paper presents a new approach where both DOE and metamodeling are integrated with a MOGA. In particular, the DOE method reduces the number of generations in a MOGA, while the metamodeling reduces the number of function calls in each generation. In the present approach, the DOE locates a subset of design points that is estimated to better sample the design space, while the metamodeling assists in estimating the fitness of design points. Several numerical and engineering examples are used to demonstrate the applicability of this new approach. The results from these examples show that the proposed improved approach requires significantly fewer function calls and obtains similar solutions compared to a conventional MOGA and a recently developed metamodeling-assisted MOGA. IS - 5 JF - Structural and Multidisciplinary Optimization EP - 461 TI - Improving multi-objective genetic algorithms with adaptive design of experiments and online metamodeling VL - 37 SP - 447 KW - design_of_experiments KW - evolutionary_algorithm KW - incremental KW - kriging KW - metamodel KW - multiobjective KW - optimization KW - pareto_front KW - uncertainty AU - Li, G AU - Li, M AU - Azarm, S AU - Al Hashimi, S AU - Al Ameri, T AU - Al Qasas, N PY - 2009/02/01/ UR - http://dx.doi.org/10.1007/s00158-008-0251-6 ER -