Finite element and neural network models for process optimization in selective laser sintering

Abstract An iterative method to optimize non-linear production processes is described. In contrast to classical design-of-experiment methods, it starts with a small number of experiments, based on which a preliminary data-based model is developed. From this model a vector of process parameters with (potentially) improved performance is calculated. The results of the experiment carried out with these new process parameters enlarge the database and result in an improved process model. The iteration is stopped if the requirements of the product properties are fulfilled. The method is applied to the selective laser sintering process of titanium powder. The goal of the optimization is to produce a ring with a prescribed geometry. One innovation of this approach is to feed the database with experimental results obtained from process simulation. The purpose of the simulation is to use the sintering machine only once to produce a part that is ‘right first time’. The simulation is based on a three-dimensional finite element model of the selective laser sintering process. The input data are the various process parameters and the model is sufficiently detailed to predict the density and the bounding quality (sintering potential) of the manufactured part.

[1]  Paul G. Klemens,et al.  Thermophysical properties of matter - the TPRC data series. Volume 1. Thermal conductivity - metallic elements and alloys. (Reannouncement). Data book , 1970 .

[2]  Rémy Glardon,et al.  3D FE simulation for temperature evolution in the selective laser sintering process , 2004 .

[3]  M. Sugeno,et al.  Structure identification of fuzzy model , 1988 .

[4]  Andrew R. Webb,et al.  Statistical Pattern Recognition , 1999 .

[5]  Wolfgang Dahmen,et al.  Introduction to Model Based Optimization of Chemical Processes on Moving Horizons , 2001 .

[6]  Karl Johan Åström,et al.  Control of complex systems , 2001 .

[7]  Ricardo H. Nochetto,et al.  Energy error estimates for a linear scheme to approximate nonlinear parabolic problems , 1987 .

[8]  J. Frenkel.  Viscous Flow of Crystalline Bodies under the Action of Surface Tension , 1945 .

[9]  László Monostori,et al.  Modelling and Monitoring of Milling through Neuro-Fuzzy Techniques , 1994 .

[10]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[11]  S.G. Duvall,et al.  A practical methodology for the statistical design of complex logic products for performance , 1995, IEEE Trans. Very Large Scale Integr. Syst..

[12]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[13]  Jan de Leeuw,et al.  Nonlinear Principal Component Analysis , 1982 .

[14]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[15]  S. Gehlen,et al.  Application of model-predictive control based on artificial neural networks to optimize the fed-batch process for riboflavin production. , 2000, Journal of biotechnology.

[16]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[17]  Dong Dong,et al.  Nonlinear principal component analysis-based on principal curves and neural networks , 1994, Proceedings of 1994 American Control Conference - ACC '94.

[18]  S.S. Rangwala,et al.  Learning and optimization of machining operations using computing abilities of neural networks , 1989, IEEE Trans. Syst. Man Cybern..

[19]  K. Kim,et al.  A New Parameterisation Method for NURBS Surface Interpolation , 2000 .

[20]  Y. S. Touloukian.  Thermophysical properties of matter , 1970 .

[21]  Eric Boillat,et al.  Finite element methods on non-conforming grids by penalizing the matching constraint , 2003 .

[22]  B. Sahakian,et al.  Spline Functions and Multivariate Interpolations , 1993 .

[23]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[24]  T. Sauer,et al.  On multivariate Lagrange interpolation , 1995 .