Using artificial neural networks and strain gauges for the determination of static loads on a thin square fully constrained composite marine panel subjected to a large central displacement.

Reza Ramazani, M., Sewell, P., Noroozi, S., Khanadan, R. and Cripps, B., 2012. Using artificial neural networks and strain gauges for the determination of static loads on a thin square fully constrained composite marine panel subjected to a large central displacement. Insight: non-destructive testing and condition monitoring, 55 (8), p. 442.

Full text available as:

[img]
Preview
PDF
Ramazani.pdf

1MB

Abstract

Current methods of estimating the behaviour of marine composite structures under pressure due to slamming as a result of high waves are based on trial and error or oversimplification. Normally under these conditions the nonlinearities of these structures are often neglected and in order to compensate, an overestimated safety factor is employed. These conservative approaches can result in heavier and overdesigned structures. In this paper a new semi-empirical method is proposed that overcomes some of these problems. This work involved the use of Artificial Neural Network (ANN) combined with strain gauge data to enable real-time in-service load monitoring of large marine structural panels. Such a tool has other important applications such as monitoring slamming or other transient hydrostatic loads that can ultimately affect their fatigue life. To develop this system a Glass Fibre Reinforced Polymer (GFRP) composite panel was used due to its potential for providing a nonlinear response to pressure or slamming loads. It was found the ANN was able to predict normal loads applied at different locations on the panel accurately. This method is also capable of predicting loads on the marine structure in real-time.

Item Type:Article
Subjects:UNSPECIFIED
Group:Faculty of Science and Technology
ID Code:20626
Deposited By: Unnamed user with email symplectic@symplectic
Deposited On:11 Feb 2013 09:46
Last Modified:11 Nov 2015 12:23

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -