NEUROCOMPUTING STRATEGIES IN STRUCTURAL DESIGN - DECOMPOSITION BASED OPTIMIZATION

The present paper introduces a scheme utilizing neurocomputing strateg ies for a decomposition approach to large scale optimization problems. In this scheme the modelling capabilities of a backpropagation neural network are employed to detect weak couplings in a system and to effe ctively decompose it into smaller, more tractable subsystems. When suc h partitioning of a design space is possible (decomposable systems), i ndependent optimization in each subsystem is performed with a penalty term added to an objective function to eliminate constraint violations in all other subsystems. Dependencies among subsystems are represente d in terms of global design variables, and since only partial informat ion is needed, a neural network is used to map relations between globa l variables and all system constraints. A feature-sensitive network (a variant of a hierarchical vector quantization technique, referred to as the HVQ network) is used for this purpose as it offers easy trainin g, approximations of an arbitrary accuracy, and processing of incomple te input vectors. The approach is illustrated with applications to min imum weight sizing of truss structures with multiple design constraint s.