Determination of optimum design spaces for topology optimization

Due to tolerances allowed in deciding the design space in preliminary designs, two approaches are proposed to find the optimum design space systematically. One is to use Taguchi orthogonal array to do experiments for some design spaces and find optimum topologies in these design spaces. The results of the experiments are used to determine the optimum boundaries of the design space. The other approach is to use genetic algorithms (GA) to search for the optimum boundaries of the design space. To reduce the computational burden of GA, the artificial neural network (ANN) is used to replace the time-consuming processes of finding optimum topologies in all individuals (design spaces) of a generation. The GA search is thus accelerated. Two examples are used to demonstrate and test the approaches. Based on numerical results the methods are reliable, practical, and efficient.

[1]  P. Hajela,et al.  GENETIC ALGORITHMS IN OPTIMIZATION PROBLEMS WITH DISCRETE AND INTEGER DESIGN VARIABLES , 1992 .

[2]  O. Sigmund,et al.  Checkerboard patterns in layout optimization , 1995 .

[3]  C. S. Jog,et al.  A new approach to variable-topology shape design using a constraint on perimeter , 1996 .

[4]  S. H. Huang,et al.  Artificial neural networks in manufacturing: concepts, applications, and perspectives , 1994 .

[5]  H. Mlejnek,et al.  An engineer's approach to optimal material distribution and shape finding , 1993 .

[6]  John A. Miller,et al.  An evaluation of local improvement operators for genetic algorithms , 1993, IEEE Trans. Syst. Man Cybern..

[7]  D. E. Goldberg,et al.  Genetic Algorithms in Search, Optimization & Machine Learning , 1989 .

[8]  Ting-Yu Chen,et al.  IMPROVEMENTS OF SIMPLE GENETIC ALGORITHM IN STRUCTURAL DESIGN , 1997 .

[9]  Prabhat Hajela,et al.  Topological optimization of rotorcraft subfloor structures for crashworthiness considerations , 1997 .

[10]  Noboru Kikuchi,et al.  Integrated optimal structural and vibration control design , 1996 .

[11]  Jr. Joseph J. Pignatiello.  An Overview of the Strategy and Tactics of Taguchi , 1988 .

[12]  M. Bendsøe,et al.  Generating optimal topologies in structural design using a homogenization method , 1988 .

[13]  A. Osyczka,et al.  A new method to solve generalized multicriteria optimization problems using the simple genetic algorithm , 1995 .

[14]  Y. Xie,et al.  Evolutionary structural optimization for problems with stiffness constraints , 1996 .

[15]  H. P. Mlejnek,et al.  Some aspects of the genesis of structures , 1992 .

[16]  Tao Jiang,et al.  A Systems Approach to Structural Topology Optimization: Designing Optimal Connections , 1997 .

[17]  Mark J. Jakiela,et al.  Generation and Classification of Structural Topologies With Genetic Algorithm Speciation , 1997 .

[18]  Y. S. Tarng,et al.  Sensing tool breakage in face milling with a neural network , 1994 .

[19]  R. Fox,et al.  Rates of change of eigenvalues and eigenvectors. , 1968 .

[20]  Marc Thomas,et al.  Comparison of a full factorial experiment to fractional and Taguchi designs in a lathe dry turning operation , 1994 .

[21]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[22]  Ren-Jye Yang,et al.  Optimal topology design using linear programming , 1994 .

[23]  N. Kikuchi,et al.  Structural topology and shape optimization for a frequency response problem , 1993 .

[24]  E. Ramm,et al.  Adaptive topology optimization , 1995 .

[25]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[26]  Ren-Jye Yang,et al.  Automotive applications of topology optimization , 1995 .