• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Doctoral Thesis
DOI
https://doi.org/10.11606/T.3.2023.tde-27042023-080040
Document
Author
Full name
Amir Muhammed Sa'ad
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 2023
Supervisor
Committee
Costa, Anna Helena Reali (President)
Brandão, Anarosa Alves Franco
Carneiro, Cleyton de Carvalho
Ferreira, Marcos Donato Auler da Silva
Sales Junior, Joel Sena
Title in English
NEMO: a neural motion estimator for mooring line failure detection of offshore platforms.
Keywords in English
Classification
Machine learning
Mooring lines breakage
Neural networks
O?shore platforms
Abstract in English
Floating oshore structures are maintained in the desired position by mooring lines attached to the seabed of the location. These systems are among the main components that guarantee not only the safety of the crew but also the various operations carried out on the platforms. In this thesis, the objective is to detect the rupture of the mooring lines of platforms with dierent levels of draft (load) based on the measurements of the platform motion provided by the Dierential Global Positioning System (DGPS) and Inertial Measurement Unit (IMU) sensors. For this, a Neural Motion Estimator (NeMo) system was developed. NeMo consists of two modules: a motion prediction module comprising of a feed forward neural network (Multilayer Perceptron MLP), which uses previous data from platform motions to predict future motion, and a multi-class classifier module, which uses the dierence between predicted motion and measured actual motion as inputs to indicate whether or not there has been a failure, for various groups of mooring lines. The system was trained and tested using simulated data from a time- domain platform motion simulator. Results of the implemented NeMo system showed it is able to detect the occurrence of failure in the mooring lines, with errors between the forecast and the measured movements when there was a line breakage. These errors are such that the developed multi-class classifier had a 99% accuracy prediction rate when classifying the platform motions.
Title in Portuguese
NEMO: um estimador de movimento neural para detecção de falha de linha de amarração de plataformas offshore.
Keywords in Portuguese
Aprendizado computacional
Classificação
Estruturas offshore
Redes Neurais
Rompimentos de cabos de ancoragem
Abstract in Portuguese
Estruturas flutuantes offshore são fixadas no local desejado por meio de cabos de amarração ancorados no fundo do mar. Esses sistemas estão entre os principais componentes que garantem não só a segurança da tripulação, mas também das diversas operações realizadas nas plataformas. Nesta tese, o objetivo é detectar a ruptura dos cabos de amarração de plataformas, com diferentes níveis de calado (carga), com base nas medidas do movimento da plataforma fornecidas pelos sensores do Sistema de Posicionamento Global Diferencial (DGPS) e da Unidade de Medição Inercial (IMU). Para isso, foi desenvolvido o sistema Neural Motion Estimator (NeMo). O sistema é composto por dois módulos: um módulo de previsão de movimento composto por uma rede feed forward (Multilayer Perceptron MLP), que usa dados prévios dos movimentos da plataforma para prever o movimento futuro, e um módulo classificador, que usa a diferença entre o movimento previsto e o movimento real medido como entradas para um classificador multiclasse que indica se houve ou não uma falha, para vários grupos de cabos de ancoragem. Os resultados do sistema NeMo mostram que ele é capaz de detectar a ocorrência de falhas nos cabos de ancoragem, mostrando erros entre os movimentos preditos e medidos quando houve um rompimento de cabo. Esses erros são tais que o classificador multiclasse desenvolvido teve uma acurácia de previsão de 99% ao classificar o movimento da plataforma.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2023-04-27
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.