Data-Driven Damage Quantification of Floating Offshore Wind Turbine Platforms Based on Multi-Scale Encoder–Decoder with Self-Attention Mechanism
A Multi-Scale Convolutional Neural Network with Self Attention-based Auto Encoder–Decoder (MSCSA-AED), is a novel high-performance framework, presented here for the quantification of damage on a multibody floating offshore wind turbine (FOWT) structure. The model is equipped with similarity measurem...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-11-01
|
Series: | Journal of Marine Science and Engineering |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-1312/10/12/1830 |
_version_ | 1797456914577096704 |
---|---|
author | Musa Bashir Zifei Xu Jin Wang C. Guedes Soares |
author_facet | Musa Bashir Zifei Xu Jin Wang C. Guedes Soares |
author_sort | Musa Bashir |
collection | DOAJ |
description | A Multi-Scale Convolutional Neural Network with Self Attention-based Auto Encoder–Decoder (MSCSA-AED), is a novel high-performance framework, presented here for the quantification of damage on a multibody floating offshore wind turbine (FOWT) structure. The model is equipped with similarity measurement to enhance its capability to accurately quantify damage effects from different scales of coded features using raw platform responses and without human intervention. Case studies using different damage magnitudes on tendons of a 10 MW multibody FOWT were used to examine the accuracy and reliability of the proposed model. The results showed that addition of Square Euclidean (SE) distance enhanced the MSCSA-AED model’s capability to suitably estimate the damage in structures operating in complex environments using only raw responses. Comparison of the model’s performance with other variants (DCN-AED and MSCNN-AED) used in the industry to extract the coded features from FOWT responses further demonstrated the superiority of MSCSA-AED in complex operating conditions, especially in low magnitude damage quantification, which is the hardest to quantify. |
first_indexed | 2024-03-09T16:14:42Z |
format | Article |
id | doaj.art-3619e72a26494294980bfafd526e0e84 |
institution | Directory Open Access Journal |
issn | 2077-1312 |
language | English |
last_indexed | 2024-03-09T16:14:42Z |
publishDate | 2022-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Marine Science and Engineering |
spelling | doaj.art-3619e72a26494294980bfafd526e0e842023-11-24T15:55:03ZengMDPI AGJournal of Marine Science and Engineering2077-13122022-11-011012183010.3390/jmse10121830Data-Driven Damage Quantification of Floating Offshore Wind Turbine Platforms Based on Multi-Scale Encoder–Decoder with Self-Attention MechanismMusa Bashir0Zifei Xu1Jin Wang2C. Guedes Soares3School of Engineering, Faculty of Engineering and Technology, Liverpool John Moores University, Liverpool L3 3AF, UKSchool of Engineering, Faculty of Engineering and Technology, Liverpool John Moores University, Liverpool L3 3AF, UKSchool of Engineering, Faculty of Engineering and Technology, Liverpool John Moores University, Liverpool L3 3AF, UKCentre for Marine Technology and Ocean Engineering (CENTEC), Instituto Superior Técnico, Universidade de Lisboa, 1649-004 Lisboa, PortugalA Multi-Scale Convolutional Neural Network with Self Attention-based Auto Encoder–Decoder (MSCSA-AED), is a novel high-performance framework, presented here for the quantification of damage on a multibody floating offshore wind turbine (FOWT) structure. The model is equipped with similarity measurement to enhance its capability to accurately quantify damage effects from different scales of coded features using raw platform responses and without human intervention. Case studies using different damage magnitudes on tendons of a 10 MW multibody FOWT were used to examine the accuracy and reliability of the proposed model. The results showed that addition of Square Euclidean (SE) distance enhanced the MSCSA-AED model’s capability to suitably estimate the damage in structures operating in complex environments using only raw responses. Comparison of the model’s performance with other variants (DCN-AED and MSCNN-AED) used in the industry to extract the coded features from FOWT responses further demonstrated the superiority of MSCSA-AED in complex operating conditions, especially in low magnitude damage quantification, which is the hardest to quantify.https://www.mdpi.com/2077-1312/10/12/1830data-driven techniquedamage quantificationfloating offshore wind turbineFOWT predictive maintenanceConvolutional Neural Networkmulti-scale information fusion |
spellingShingle | Musa Bashir Zifei Xu Jin Wang C. Guedes Soares Data-Driven Damage Quantification of Floating Offshore Wind Turbine Platforms Based on Multi-Scale Encoder–Decoder with Self-Attention Mechanism Journal of Marine Science and Engineering data-driven technique damage quantification floating offshore wind turbine FOWT predictive maintenance Convolutional Neural Network multi-scale information fusion |
title | Data-Driven Damage Quantification of Floating Offshore Wind Turbine Platforms Based on Multi-Scale Encoder–Decoder with Self-Attention Mechanism |
title_full | Data-Driven Damage Quantification of Floating Offshore Wind Turbine Platforms Based on Multi-Scale Encoder–Decoder with Self-Attention Mechanism |
title_fullStr | Data-Driven Damage Quantification of Floating Offshore Wind Turbine Platforms Based on Multi-Scale Encoder–Decoder with Self-Attention Mechanism |
title_full_unstemmed | Data-Driven Damage Quantification of Floating Offshore Wind Turbine Platforms Based on Multi-Scale Encoder–Decoder with Self-Attention Mechanism |
title_short | Data-Driven Damage Quantification of Floating Offshore Wind Turbine Platforms Based on Multi-Scale Encoder–Decoder with Self-Attention Mechanism |
title_sort | data driven damage quantification of floating offshore wind turbine platforms based on multi scale encoder decoder with self attention mechanism |
topic | data-driven technique damage quantification floating offshore wind turbine FOWT predictive maintenance Convolutional Neural Network multi-scale information fusion |
url | https://www.mdpi.com/2077-1312/10/12/1830 |
work_keys_str_mv | AT musabashir datadrivendamagequantificationoffloatingoffshorewindturbineplatformsbasedonmultiscaleencoderdecoderwithselfattentionmechanism AT zifeixu datadrivendamagequantificationoffloatingoffshorewindturbineplatformsbasedonmultiscaleencoderdecoderwithselfattentionmechanism AT jinwang datadrivendamagequantificationoffloatingoffshorewindturbineplatformsbasedonmultiscaleencoderdecoderwithselfattentionmechanism AT cguedessoares datadrivendamagequantificationoffloatingoffshorewindturbineplatformsbasedonmultiscaleencoderdecoderwithselfattentionmechanism |