Multiple Damage Detection of an Offshore Helideck through the Two-Step Artificial Neural Network Based on the Limited Mode Shape Data.

Byungmo Kim,Seung-Hyun Ha,Chanyeong Kim

doi:10.3390/s21217357

Byungmo Kim, Seung-Hyun Ha + Show 1 more

Open Access

https://doi.org/10.3390/s21217357

Copy DOI

Abstract

A helideck is an essential structure in an offshore platform, and it is crucial to maintain its structural integrity and detect the occurrence of damage early. Because helidecks usually consist of complex lattice truss members, precise measurements are required for structural health monitoring based on accurate modal parameters. However, available sensors and data acquisition are limited. Therefore, we propose a two-step damage detection process using an artificial neural network. Based on the mode shape database collected from 137,400 damage scenarios by finite element analysis, the neural network in the first step was trained to estimate the mode shapes of the entire helideck model using the selected mode shape data obtained from the limited measuring points. Then, the neural network in the second step is consecutively trained to detect the location and amount of structural damage to individual parts. As a result, it is shown that the proposed procedure provides the damage detection capability with only a quarter of the entire mode shape data, while the estimation accuracy is sufficiently high compared to the single network directly trained using all mode shape data. It was also found that, compared to the network directly trained from the same data, the proposed technique tends to detect minor damages more accurately.

Highlights

Offshore structures encounter various hazards during long operation periods
This study developed a multilayer perceptron (MLP) that provides the location and severity of damages from natural frequencies and mode shapes based on the simulation model of a cantilever-type offshore helideck designed by [7]
The blue and orange lines show the losses for the training and validation data, respectively

Summary

Introduction

Hazards sometimes cause serious consequences such as explosions, collapses, or capsizes. Under such situations, offshore helidecks are the final exit that people on the platform can use to escape. There are some design codes to follow in designing helidecks, such as CAA-CAP-437 [1], DNV-OS-E401 [2], and API-APR-RP-2L [3]. Based on these standards, several studies have proposed safe designs for helidecks. A cantilever-type lightweight helideck design was proposed using topology optimization, and the sectional dimensions of its members were determined by parameter studies [5]. To propose a helideck design that has merit in manufacturing and satisfies conservative and persuasive design criteria for customers, a design domain comprising the arranged section numbers within a pool of commercial steel section products was established, and the optimal design was found using a genetic algorithm with safety constraints using the

Methods

Results

Conclusion