An adaptive neural network strategy for improving the computational performance of evolutionary structural optimization

This work is focused on improving the computational efficiency of evolutionary algorithms implemented in large-scale structural optimization problems. Locating optimal structural designs using evolutionary algorithms is a task associated with high computational cost, since a complete finite element (FE) analysis needs to be carried out for each parent and offspring design vector of the populations considered. Each of these FE solutions facilitates decision making regarding the feasibility or infeasibility of the corresponding structural design by evaluating the displacement and stress constraints specified for the structural problem at hand. This paper presents a neural network (NN) strategy to reliably predict, in the framework of an evolution strategies (ES) procedure for structural optimization, the feasibility or infeasibility of structural designs avoiding computationally expensive FE analyses. The proposed NN implementation is adaptive in the sense that the utilized NN configuration is appropriately updated as the ES process evolves by performing NN retrainings using information gradually accumulated during the ES execution. The prediction capabilities and the computational advantages offered by this adaptive NN scheme coupled with domain decomposition solution techniques are investigated in the context of design optimization of skeletal structures on both sequential and parallel computing environments.

[1]  Manolis Papadrakakis,et al.  Subdomain cluster generation for domain decomposition methods using graph partitioning optimization , 2003 .

[2]  Hans-Paul Schwefel,et al.  Numerical Optimization of Computer Models , 1982 .

[3]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[4]  Charbel Farhat,et al.  Implicit parallel processing in structural mechanics , 1994 .

[5]  M. Zako,et al.  Structural optimization using Kriging approximation , 2003 .

[6]  Manolis Papadrakakis,et al.  Reliability-based structural optimization using neural networks and Monte Carlo simulation , 2002 .

[7]  Prabhat Hajela,et al.  Counterpropagation neural networks in decomposition based optimal design , 1997 .

[8]  Layne T. Watson,et al.  COMPOSITE LAMINATE DESIGN OPTIMIZATION BY GENETIC ALGORITHM WITH GENERALIZED ELITIST SELECTION , 2001 .

[9]  Manolis Papadrakakis,et al.  Structural reliability analyis of elastic-plastic structures using neural networks and Monte Carlo simulation , 1996 .

[10]  Asim Karim,et al.  Neural Network Model for Optimization of Cold-Formed Steel Beams , 1997 .

[11]  Thomas Bäck,et al.  An Overview of Evolutionary Algorithms for Parameter Optimization , 1993, Evolutionary Computation.

[12]  C. Farhat,et al.  The second generation FETI methods and their application to the parallel solution of large-scale linear and geometrically non-linear structural analysis problems , 2000 .

[13]  D. Rixen,et al.  A simple and efficient extension of a class of substructure based preconditioners to heterogeneous structural mechanics problems , 1999 .

[14]  Y. Xie,et al.  Stiffness and inertia multicriteria evolutionary structural optimisation , 2001 .

[15]  Carlos Artemio Coello-Coello,et al.  Theoretical and numerical constraint-handling techniques used with evolutionary algorithms: a survey of the state of the art , 2002 .

[16]  Manolis Papadrakakis,et al.  Parallel computational strategies for structural optimization , 2003 .

[17]  M. Papadrakakis,et al.  Structural optimization using evolutionary algorithms , 2002 .

[18]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[19]  Jack Dongarra,et al.  PVM: Parallel virtual machine: a users' guide and tutorial for networked parallel computing , 1995 .

[20]  Barry Hilary Valentine Topping,et al.  Neural Computing for Structural Mechanics , 1999 .

[21]  Srinivas Kodiyalam,et al.  Neural networks with modified backpropagation learning applied to structural optimization , 1996 .

[22]  Carlos A. Coello Coello,et al.  THEORETICAL AND NUMERICAL CONSTRAINT-HANDLING TECHNIQUES USED WITH EVOLUTIONARY ALGORITHMS: A SURVEY OF THE STATE OF THE ART , 2002 .

[23]  Rong C. Shieh,et al.  Massively parallel structural design using stochastic optimization and mixed neuralnet/finite element analysis methods , 1994 .

[24]  Manolis Papadrakakis,et al.  The mosaic of high performance domain Decomposition Methods for Structural Mechanics: Formulation, interrelation and numerical efficiency of primal and dual methods , 2003 .

[25]  Li Zhang,et al.  An evaluation of back-propagation neural networks for the optimal design of structural systems: Part II. Numerical evaluation , 2002 .

[26]  Manolis Papadrakakis,et al.  STRUCTURAL SHAPE OPTIMIZATION USING EVOLUTION STRATEGIES , 1999 .

[27]  Manolis Papadrakakis,et al.  Enhancing the performance of the FETI method with preconditioning ¶techniques implemented on clusters of networked computers , 2002 .

[28]  Gregory W. Brown,et al.  Mesh partitioning for implicit computations via iterative domain decomposition: Impact and optimization of the subdomain aspect ratio , 1995 .

[29]  Manolis Papadrakakis,et al.  Soft computing methodologies for structural optimization , 2003, Appl. Soft Comput..

[30]  Hojjat Adeli,et al.  Bilevel Parallel Genetic Algorithms for Optimization of Large Steel Structures , 2001 .

[31]  Martin T. Hagan,et al.  Gauss-Newton approximation to Bayesian learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[32]  A W Beeby,et al.  CONCISE EUROCODE FOR THE DESIGN OF CONCRETE BUILDINGS. BASED ON BSI PUBLICATION DD ENV 1992-1-1: 1992. EUROCODE 2: DESIGN OF CONCRETE STRUCTURES. PART 1: GENERAL RULES AND RULES FOR BUILDINGS , 1993 .

[33]  Mattias Björkman,et al.  Global Optimization of Costly Nonconvex Functions Using Radial Basis Functions , 2000 .

[34]  Jongsoo Lee,et al.  Constrained genetic search via schema adaptation: An immune network solution , 1996 .

[35]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[36]  Michael I. Jordan,et al.  Neural networks , 1996, CSUR.