Abstract
Genetic algorithms are well established for solving engineering optimization problems having both continuous and discrete design variables. In this paper, a mutation function for discrete design variables based on Data Mining is introduced. The M5P Data Mining algorithm is used to build rules for the prediction of the optimization objectives with respect to the discrete design variables. The most promising combinations of discrete design variables are then selected in the mutation function of the genetic algorithm GAME to create children. This approach results in faster convergence and better results for both single and multi-objective problems when compared with a standard mutation scheme of discrete design variables. The optimization of a vehicle space frame showed that a mutation probability between 40% and 60% for the discrete design variables results in the fastest convergence. A multi-objective aerospace conceptual design example showed a substantial improvement in the number of pareto-optimal solutions found after 100 generations.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aggarwal Y (2007) Modeling of reinforcement in concrete beams using machine learning tools. In: Proceeding of world academy of science, engineering and technology, vol 32, pp 253–257
Braun RD, Kroo IM (1995) Development and application of the collaborative optimization architecture in a multidisciplinary design environment. Tech. rep., NASA Langley Technical Report Server
Bremicker M, Papalambros P, Loh H (1990) Solution of mixed-discrete structural optimization problems with a new sequential linearization algorithm. Comput Struct 37(4):451–461. doi:10.1016/0045-7949(90)90035-Z
Chen TY, Chen HC (2009) Mixed-discrete structural optimization using a rank-niche evolution strategy. Eng Optim 41(1):39–58
Deb K, Pratap A, Agarwal S, Meyarivan T (2002) A fast and elitist multiobjective genetic algorithm: NSGA-II. Evol Comput, IEEE Trans 6(2):182–197. doi:10.1109/4235.996017
Fonseca CM, Fleming PJ (1993) Genetic algorithms for multiobjective optimization: formulation, discussion and generalization. In: Proceedings of the fifth international conference on genetic algorithms, vol 423
Gutkowski W, Bauer J (eds) (1994) Discrete structural optimization. IUTAM. Springer, New York
Hajela P, Szewczyk ZP (1994) Neurocomputing strategies in structural design—on analysing weights of feedforward neural networks. Struct Multidiscipl Optim 8(4):236–241. doi:10.1007/BF01742708
Hand DJ, Mannila H, Smyth P (2001) Principles of data mining. Adaptive computation and machine learning. MIT, Cambridge
Huber M, Petersson Ö (2007) Completeness of problem formulation via knowledge-based models. In: Proceedings of the EUROMECH colloquium 482 - efficient method for robust design and optimization. London, GB
Huber M, Petersson Ö, Baier H (2008) Knowledge-based modeling of manufacturing aspects in structural optimization problems. Adv Mat Res 43:111–122
Langer H (2005) Extended evolutionary algorithms for multiobjective and discretedesign optimization of structures. PhD thesis, Institute for Lightweight Structures—Technische Universität München
Langer H, Pühlhofer T, Baier H (2004) A multiobjective evolutionary algorithm with integrated response surface functionalities for configuration optimization with discrete variables. In: Proceedings of the 10th AIAA/ISSMO multidisciplinary analysis and optimization conference
Lin J (2004) Analysis and enhancement of collaborative optimization for multidisciplinary design. AIAA J 42(2):348–360
Neufeld D, Chung J (2005) Unmanned aerial vehicle conceptual design using a genetic algorithm and data mining. Infotech@ Aerospoace pp 1–25
Neufeld D, Joon C (2008) Development of a flexible MDO architecture for aircraft conceptual design. In: Proceedings of the 2008 EngOpt conference. Rio de Jenario, Brazil
Pant R, Fielding JP (1999) Aircraft configuration and flight profile optimization using simulated annealing. Aircraft Design 2(4):239–255. doi:10.1016/S1369-8869(99)00020-8
Pietzka D, Schikorra M, Tekkaya E (2008) Embedding of alumina reinforcing elements in the composite extrusion process. Adv Mat Res 43:9–16
Pühlhofer T, Langer H, Baier H, Huber M (2004) Multicriteria and discrete configuration and design optimization with applications for satellites. In: Collection of technical papers - 10th AIAA/ISSMO multidisciplinary analysis and optimization conference, vol 5, pp 2832–2835
Quinlan JR (1992) Learning with continuous classes. In: 5th Australian joint conference on artificial intelligence, pp 343–348
Schäfer E, Geilen J, Eschenauer HA (1993) Application of discrete optimization techniques to optimal composite structures optimization in aircraft conceptual design. In: Gutkowski W, Bauer J (eds) Discrete structural optimization. Proceedings of the IUTAM symposium in Zakopane, Poland, 31 August–3 September. IUTAM, Springer
Sellar RS, Batill SM, Renaud JE (1994) Optimization of mixed discrete/continuous design variable systems using neural networks. In: Proceedings of the fifth AIAA/USAF/NASA/ISSMO symposium on multidisciplinary analysis and optimization. Panama City, Florida, pp 7–9
Sobieszczanski-Sobieski J, Haftka RT (1997) Multidisciplinary aerospace design optimization: survey of recent developments. Struct Multidiscipl Optim 14(1):1–23. doi:10.1007/BF01197554
Stelmack MA, Batill SM (1997) Concurrent subspace optimization of mixed continuous/discrete systems. In: Collection of technical papers - AIAA/ASME/ASCE/AHS/ASC structures, structural dynamics and materials conference, vol 2, pp 1303–1315
Stelmack MA, Batill SM, Beck BC, Flask DJ (1998) Application of the concurrent subspace design framework to aircraft brake component design optimization. In: Collection of technical papers - AIAA/ASME/ASCE/AHS/ASC structures, structural dynamics and materials conference, vol 4, pp 2750–2760
Swift R, Batill S (1992) Simulated annealing utilizing neural networks for discrete design variable optimization problems in structural design. In: AIAA/ASME/AHS/ASC 33rd structures, structural dynamics and materials conference, AIAA 92-2311, February 1992
Szewczyk ZP, Hajela P (1994) Neurocomputing strategies in structural design—decomposition based optimization. Struct Multidiscipl Optim 8(4):242–250. doi:10.1007/BF01742709
Weidenmann K, Kerscher E, Schulze V, Löhe D (2006) Mechanical properties of wire-reinforced aluminium extrusions under quasi-static loading conditions. Adv Mat Res 10:23–34
Weinert K, Fleischer J, Tekkaya A, Zäh M, Schikorra M (2008) Flexible manufacturing of lightweight frame structures - phase ii: intergartion. Adv Mat Res 43. doi:10.4028/www.scientific.net/AMR.43
Wetter M, Wright J (2004) A comparison of deterministic and probabilistic optimization algorithms for nonsmooth simulation-based optimization. Build Environ 39(8):989–999
Witten IH (1999) Weka: practical machine learning tools and techniques with java implementations. Dept. of Computer Science, University of Waikato
Wu X, Kumar V, Quinlan JR, Ghosh J, Yang Q, Motoda H, McLachlan G, Ng A, Liu B, Yu P, Zhou Z, Steinbach M, Hand D, Steinberg D (2008) Top 10 algorithms in data mining. Knowl Inf Syst 14(1):1–37. doi:10.1007/s10115-007-0114-2
Author information
Authors and Affiliations
Corresponding author
Additional information
This paper is based partially on investigations of the collaborative research center SFB/TR10, which is kindly supported by the German Research Foundation (DFG). The research visit of Mr. Daniel Neufeld was made possible by DFG funding.
Rights and permissions
About this article
Cite this article
Huber, M., Neufeld, D., Chung, J. et al. Data Mining based mutation function for engineering problems with mixed continuous-discrete design variables. Struct Multidisc Optim 41, 589–604 (2010). https://doi.org/10.1007/s00158-009-0439-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00158-009-0439-4