Structural health monitoring of offshore structures

  • Authors:

  • S. A. Mourad;A. W. Sadek;A. F. Batisha

  • Affiliations:

  • Structural Engineering Dept., Engineering Faculty, Cairo University, Egypt;Kuwait Institute For Scientific Research, Kuwait;Environmental and Climate Research Institute, National Water Research Center, Egypt

  • Venue:
  • ICAAICSE '01 Proceedings of the sixth international conference on Application of artificial intelligence to civil & structural engineering
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

Abstract

Neural networks are a computational model composed of a highly interconnected mesh of nonlinear elements and whose structure is inspired by the biological nervous system. Two neural network architectures are proposed to assess the structural integrity of offshore fixed platforms. The first network depends on monitoring of the natural frequencies of the structure to determine its status. The second accounts for the structural response - represented by the deck drift due to environmental loading - to judge the performance of the structure. The networks were trained using samples generated by a finite element package. The two neural networks are used for decisions regarding inspection and repair of offshore structures. Application may be extended into an integral system for automatic damage detection and for classification and identification of multiple defects.