Neural networks on fatigue damage prediction

Author

Lopes, Tiago Alberto Piedras

Author_Institution

COPPE, Univ. Federal do Rio de Janeiro, Brazil

Volume

1

fYear

1997

fDate

9-12 Jun 1997

Firstpage

183

Abstract

This paper introduces a new methodology for fatigue evaluation of tubular offshore structures. The accumulated fatigue damage on selected joints, caused by actual wave loading condition, is assessed through a data acquisition and processing system, based on a PC microcomputer, installed onboard. By measuring the upward jacket displacements and applying feedforward backpropagation trained neural networks, the calculation of fatigue damage is performed in-time. This information, along with inspection reports, could be used to improve further inspection and repair of the platform structural joints

Keywords

backpropagation; data acquisition; displacement measurement; fatigue; feedforward neural nets; microcomputer applications; structural engineering computing; accumulated fatigue damage; data acquisition and processing system; fatigue damage prediction; feedforward backpropagation trained neural networks; inspection reports; tubular offshore structures; upward jacket displacements; wave loading condition; Artificial neural networks; Automatic control; Data acquisition; Equations; Fatigue; Feedforward neural networks; Inspection; Neural networks; Stochastic processes; Stress;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks,1997., International Conference on

Conference_Location

Houston, TX

Print_ISBN

0-7803-4122-8

Type

conf

DOI

10.1109/ICNN.1997.611661

Filename

611661