Data management for structural integrity assessment of offshore wind turbine support structures: data cleansing and missing data imputation

Maria Martinez-Luengo, Mahmood Shafiee, Athanasios Kolios

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Structural Health Monitoring (SHM) and Condition Monitoring (CM) Systems are currently utilised to collect data from offshore wind turbines (OWTs), to enhance the accurate estimation of their operational performance. However, industry accepted practices for effectively managing the information that these systems provide have not been widely established yet. This paper presents a four-step methodological framework for the effective data management of SHM systems of OWTs and illustrates its applicability in real-time continuous data collected from three operational units, with the aim of utilising more complete and accurate datasets for fatigue life assessment of support structures. Firstly, a time-efficient synchronisation method that enables the continuous monitoring of these systems is presented, followed by a novel approach to noise cleansing and the posterior missing data imputation (MDI). By the implementation of these techniques those data-points containing excessive noise are removed from the dataset (Step 2), advanced numerical tools are employed to regenerate missing data (Step 3) and fatigue is estimated for the results of these two methodologies (Step 4). Results show that after cleansing, missing data can be imputed with an average absolute error of 2.1%, while this error is kept within the [+ 15.2%−11.0%] range in 95% of cases. Furthermore, only 0.15% of the imputed data fell outside the noise thresholds. Fatigue is found to be underestimated both, when data cleansing does not take place and when it takes place but MDI does not. This makes this novel methodology an enhancement to conventional structural integrity assessment techniques that do not employ continuous datasets in their analyses.

LanguageEnglish
Pages867-883
Number of pages17
JournalOcean Engineering
Volume173
DOIs
Publication statusPublished - 1 Feb 2019

Fingerprint

Offshore wind turbines
Structural integrity
Information management
Structural health monitoring
Fatigue of materials
Condition monitoring
Synchronization
Monitoring
Industry

Keywords

  • artificial neural network (ANN)
  • data synchronisation
  • missing data imputation
  • noise cleansing
  • offshore wind
  • structural health monitoring (SHM)

Cite this

@article{0ac3f0d7a6144d1abd91cade6085094c,
title = "Data management for structural integrity assessment of offshore wind turbine support structures: data cleansing and missing data imputation",
abstract = "Structural Health Monitoring (SHM) and Condition Monitoring (CM) Systems are currently utilised to collect data from offshore wind turbines (OWTs), to enhance the accurate estimation of their operational performance. However, industry accepted practices for effectively managing the information that these systems provide have not been widely established yet. This paper presents a four-step methodological framework for the effective data management of SHM systems of OWTs and illustrates its applicability in real-time continuous data collected from three operational units, with the aim of utilising more complete and accurate datasets for fatigue life assessment of support structures. Firstly, a time-efficient synchronisation method that enables the continuous monitoring of these systems is presented, followed by a novel approach to noise cleansing and the posterior missing data imputation (MDI). By the implementation of these techniques those data-points containing excessive noise are removed from the dataset (Step 2), advanced numerical tools are employed to regenerate missing data (Step 3) and fatigue is estimated for the results of these two methodologies (Step 4). Results show that after cleansing, missing data can be imputed with an average absolute error of 2.1{\%}, while this error is kept within the [+ 15.2{\%}−11.0{\%}] range in 95{\%} of cases. Furthermore, only 0.15{\%} of the imputed data fell outside the noise thresholds. Fatigue is found to be underestimated both, when data cleansing does not take place and when it takes place but MDI does not. This makes this novel methodology an enhancement to conventional structural integrity assessment techniques that do not employ continuous datasets in their analyses.",
keywords = "artificial neural network (ANN), data synchronisation, missing data imputation, noise cleansing, offshore wind, structural health monitoring (SHM)",
author = "Maria Martinez-Luengo and Mahmood Shafiee and Athanasios Kolios",
year = "2019",
month = "2",
day = "1",
doi = "10.1016/j.oceaneng.2019.01.003",
language = "English",
volume = "173",
pages = "867--883",
journal = "Ocean Engineering",
issn = "0029-8018",
publisher = "Elsevier",

}

Data management for structural integrity assessment of offshore wind turbine support structures : data cleansing and missing data imputation. / Martinez-Luengo, Maria; Shafiee, Mahmood; Kolios, Athanasios.

In: Ocean Engineering, Vol. 173, 01.02.2019, p. 867-883.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Data management for structural integrity assessment of offshore wind turbine support structures

T2 - Ocean Engineering

AU - Martinez-Luengo, Maria

AU - Shafiee, Mahmood

AU - Kolios, Athanasios

PY - 2019/2/1

Y1 - 2019/2/1

N2 - Structural Health Monitoring (SHM) and Condition Monitoring (CM) Systems are currently utilised to collect data from offshore wind turbines (OWTs), to enhance the accurate estimation of their operational performance. However, industry accepted practices for effectively managing the information that these systems provide have not been widely established yet. This paper presents a four-step methodological framework for the effective data management of SHM systems of OWTs and illustrates its applicability in real-time continuous data collected from three operational units, with the aim of utilising more complete and accurate datasets for fatigue life assessment of support structures. Firstly, a time-efficient synchronisation method that enables the continuous monitoring of these systems is presented, followed by a novel approach to noise cleansing and the posterior missing data imputation (MDI). By the implementation of these techniques those data-points containing excessive noise are removed from the dataset (Step 2), advanced numerical tools are employed to regenerate missing data (Step 3) and fatigue is estimated for the results of these two methodologies (Step 4). Results show that after cleansing, missing data can be imputed with an average absolute error of 2.1%, while this error is kept within the [+ 15.2%−11.0%] range in 95% of cases. Furthermore, only 0.15% of the imputed data fell outside the noise thresholds. Fatigue is found to be underestimated both, when data cleansing does not take place and when it takes place but MDI does not. This makes this novel methodology an enhancement to conventional structural integrity assessment techniques that do not employ continuous datasets in their analyses.

AB - Structural Health Monitoring (SHM) and Condition Monitoring (CM) Systems are currently utilised to collect data from offshore wind turbines (OWTs), to enhance the accurate estimation of their operational performance. However, industry accepted practices for effectively managing the information that these systems provide have not been widely established yet. This paper presents a four-step methodological framework for the effective data management of SHM systems of OWTs and illustrates its applicability in real-time continuous data collected from three operational units, with the aim of utilising more complete and accurate datasets for fatigue life assessment of support structures. Firstly, a time-efficient synchronisation method that enables the continuous monitoring of these systems is presented, followed by a novel approach to noise cleansing and the posterior missing data imputation (MDI). By the implementation of these techniques those data-points containing excessive noise are removed from the dataset (Step 2), advanced numerical tools are employed to regenerate missing data (Step 3) and fatigue is estimated for the results of these two methodologies (Step 4). Results show that after cleansing, missing data can be imputed with an average absolute error of 2.1%, while this error is kept within the [+ 15.2%−11.0%] range in 95% of cases. Furthermore, only 0.15% of the imputed data fell outside the noise thresholds. Fatigue is found to be underestimated both, when data cleansing does not take place and when it takes place but MDI does not. This makes this novel methodology an enhancement to conventional structural integrity assessment techniques that do not employ continuous datasets in their analyses.

KW - artificial neural network (ANN)

KW - data synchronisation

KW - missing data imputation

KW - noise cleansing

KW - offshore wind

KW - structural health monitoring (SHM)

UR - http://www.scopus.com/inward/record.url?scp=85061324147&partnerID=8YFLogxK

UR - https://www.sciencedirect.com/journal/ocean-engineering

U2 - 10.1016/j.oceaneng.2019.01.003

DO - 10.1016/j.oceaneng.2019.01.003

M3 - Article

VL - 173

SP - 867

EP - 883

JO - Ocean Engineering

JF - Ocean Engineering

SN - 0029-8018

ER -