Evolutionary multi-objective optimization and decision making for selective laser sintering

This paper proposes an integrated approach to arrive at optimal build orientations, simultaneously minimizing surface roughness `Ra' and build time `T', for object manufacturing in SLS process. The optimization task is carried out by two popularly known multi-objective evolutionary optimizers - NSGA-II (non-dominated sorting genetic algorithm) and MOPSO (multi-objective particle swarm optimizer). The performance comparison of these two optimizers along with an approximation of Pareto-optimal front is done using two statistically significant performance measures. Three proposals addressing the task of decision making, i.e. selecting one solution in presence of multiple trade-off solutions, are introduced to facilitate the designer. The overall procedure is integrated into MORPE - Multi-objective Rapid Prototyping Engine. Several sample objects are considered for experimentation to demonstrate the working of MORPE. A careful study of optimal build directions for several components indicates a trend, providing insight into the SLS processes which can be regarded highly useful for various practical RP applications.

[1]  Jürgen Branke,et al.  Empirical comparison of MOPSO methods - Guide selection and diversity preservation - , 2009, 2009 IEEE Congress on Evolutionary Computation.

[2]  Nikhil Padhye.  Topology optimization of compliant mechanism using multi-objective particle swarm optimization , 2008, GECCO '08.

[3]  H. S. Byun,et al.  Determination of the optimal part orientation in layered manufacturing using a genetic algorithm , 2005 .

[4]  Nikhil Padhye,et al.  Rapid prototyping using evolutionary approaches: part 2 , 2009, GECCO '09.

[5]  Andrew Y. C. Nee,et al.  Multi‐objective optimization of part‐ building orientation in stereolithography , 1995 .

[6]  P. M. Pandey,et al.  Optimal part deposition orientation in FDM by using a multicriteria genetic algorithm , 2004 .

[7]  Joshua D. Knowles.  A summary-attainment-surface plotting method for visualizing the performance of stochastic multiobjective optimizers , 2005, 5th International Conference on Intelligent Systems Design and Applications (ISDA'05).

[8]  Nikhil Padhye.  Comparison of archiving methods in multi-objectiveparticle swarm optimization (MOPSO): empirical study , 2009, GECCO '09.

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

[10]  Kaisa Miettinen,et al.  Nonlinear multiobjective optimization , 1998, International series in operations research and management science.

[11]  Ming-Chuan Leu,et al.  Progress in Additive Manufacturing and Rapid Prototyping , 1998 .

[12]  Georges Fadel,et al.  Expert system-based selection of the preferred direction of build for rapid prototyping processes , 1995, J. Intell. Manuf..

[13]  A. K. Nagpal,et al.  Optimum part deposition orientation for multiple objectives in SL and SLS prototyping , 2009 .

[14]  N. Venkata Reddy,et al.  Optimum part deposition orientation in fused deposition modeling , 2004 .

[15]  Ho-Chan Kim,et al.  Fabrication direction optimization to minimize post-machining in layered manufacturing , 2007 .

[16]  Eckart Zitzler,et al.  Evolutionary algorithms for multiobjective optimization: methods and applications , 1999 .

[17]  N. Venkata Reddy,et al.  Part deposition orientation studies in layered manufacturing , 2007 .

[18]  Kaisa Miettinen,et al.  Some Methods for Nonlinear Multi-objective Optimization , 2001, EMO.