30 March 2006 Structural health monitoring of composite T-joints for assessing the integrity of damage zones
Author Affiliations +
Abstract
This paper uses one category of Structural Health Monitoring (SHM) which uses strain variation across a structure as the key to damage detection. The structure used in this study was made from Glass Fibre Reinforced Plastic (GFRP). This paper discusses a technique developed called "Global Neural network Architecture Incorporating Sequential Processing of Internal sub Networks (GNAISPIN)" to predict the presence of multiple damage zones, determine their positions and also predict the extent of damage. Finite Element (FE) models of T-joints, used in ship structures, were created using MSC Patran(R) . These FE models were created with delaminations embedded at various locations across the bond-line of the structure. The resulting strain variation across the surface of the structure was observed. The validity of the Finite Element model was then verified experimentally. GNAISPIN was then used in tandem with the Damage Relativity Analysis Technique to predict and estimate the presence of multiple delaminations.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
A. Kesavan, M. Deivasigamani, Sabu J. John, Israel Herszberg, "Structural health monitoring of composite T-joints for assessing the integrity of damage zones", Proc. SPIE 6167, Smart Structures and Materials 2006: Smart Sensor Monitoring Systems and Applications, 61670E (30 March 2006); doi: 10.1117/12.655967; https://doi.org/10.1117/12.655967
PROCEEDINGS
12 PAGES


SHARE
KEYWORDS
Sensors

Neurons

Composites

Structural health monitoring

Neural networks

Artificial neural networks

Glasses

Back to Top