Multi-objective Topology Optimization of Electrical Machine Designs Using Evolutionary Algorithms with Discrete and Real Encodings

We describe initial results obtained when applying different multi-objective evolutionary algorithms (MOEAs) to direct topology optimization (DTO) scenarios that are relevant in the field of electrical machine design. Our analysis is particularly concerned with investigating if the use of discrete or real-value encodings combined with a preference for a particular population initialization strategy can have a severe impact on the performance of MOEAs applied for DTO.

[1]  Johannes Gerstmayr,et al.  Coupled optimization in MagOpt , 2016, J. Syst. Control. Eng..

[2]  Mark Fleischer,et al.  The measure of pareto optima: Applications to multi-objective metaheuristics , 2003 .

[3]  Chang-Hwan Im,et al.  Hybrid genetic algorithm for electromagnetic topology optimization , 2003 .

[4]  Jouni Lampinen,et al.  GDE3: the third evolution step of generalized differential evolution , 2005, 2005 IEEE Congress on Evolutionary Computation.

[5]  Edwin Lughofer,et al.  Hybridization of multi-objective evolutionary algorithms and artificial neural networks for optimizing the performance of electrical drives , 2013, Eng. Appl. Artif. Intell..

[6]  Ingo Hahn,et al.  Kriging-Assisted Multi-Objective Particle Swarm Optimization of permanent magnet synchronous machine for hybrid and electric cars , 2013, 2013 International Electric Machines & Drives Conference.

[7]  Edwin Lughofer,et al.  DECMO2: a robust hybrid and adaptive multi-objective evolutionary algorithm , 2014, Soft Computing.

[8]  Qingfu Zhang,et al.  MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition , 2007, IEEE Transactions on Evolutionary Computation.

[9]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[10]  R. K. Ursem.  Multi-objective Optimization using Evolutionary Algorithms , 2009 .

[11]  Edwin Lughofer,et al.  Efficient Multi-Objective Optimization Using 2-Population Cooperative Coevolution , 2013, EUROCAST.

[12]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..