Application of Artificial Neural Networks to Composite Ply Micromechanics

See related content

by D. A. Brown, Co of Wooster, Wooster, United States,
P. L. N. Murthy, Co of Wooster, Wooster, United States,
L. Berke, Co of Wooster, Wooster, United States,

Document Type: Proceeding Paper

Part of: Mechanics Computing in 1990's and Beyond

Abstract: Artificial neural networks can provide improved computational efficiency relative to existing methods when algorithmic description of functional relationships is either totally unavailable or is complex in nature. Because of the natural parallelism of the neural network model, the calculations of a neural network are easily decomposed for simultaneous calculation on multiple computer processors. For complex calculations, significant reductions in elapsed computation time are possible. The primary goal of this project is to demonstrate the applicability of artificial neural networks to composite material characterization. As a test case, a neural network has been trained to accurately predict composite hygral, thermal, and mechanical properties when provided with basic information concerning the environment, constituent materials, and component ratios used in the creation of the composite.

Subject Headings: Composite materials | Neural networks | Materials characterization | Computer models | Thermal properties | Micromechanics |

Services: Buy this book/Buy this article


Return to search