NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Neurocomputing strategies in decomposition based structural designThe present paper explores the applicability of neurocomputing strategies in decomposition based structural optimization problems. It is shown that the modeling capability of a backpropagation neural network can be used to detect weak couplings in a system, and to effectively decompose it into smaller, more tractable, subsystems. When such partitioning of a design space is possible, parallel optimization can be performed in each subsystem, with a penalty term added to its objective function to account for constraint violations in all other subsystems. Dependencies among subsystems are represented in terms of global design variables, and a neural network is used to map the relations between these variables and all subsystem constraints. A vector quantization technique, referred to as a z-Network, can effectively be used for this purpose. The approach is illustrated with applications to minimum weight sizing of truss structures with multiple design constraints.
Document ID
19930050122
Document Type
Conference Paper
Authors
Szewczyk, Z. (NASA Langley Research Center Hampton, VA, United States)
Hajela, P. (Rensselaer Polytechnic Inst. Troy, NY, United States)
Date Acquired
August 16, 2013
Publication Date
January 1, 1993
Publication Information
Publication: In: AIAA(ASME)ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference, 34th and AIAA/ASME Adaptive Structures Forum, La Jolla, CA, Apr. 19-22, 1993, Technical Papers. Pt. 4 (A93-33876 1
Subject Category
CYBERNETICS
Report/Patent Number
AIAA PAPER 93-1587
Funding Number(s)
CONTRACT_GRANT: NAG1-1269
Distribution Limits
Public
Copyright
Other

Related Records

IDRelationTitle19930049879Analytic PrimaryAIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference, 34th and AIAA/ASME Adaptive Structures Forum, La Jolla, CA, Apr. 19-22, 1993, Technical Papers. Pts. 1-6