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

Martínez-Luengo, María; Shafiee, Mahmood; Kolios, Athanasios

doi:10.1016/j.oceaneng.2019.01.003

Cited by 53 publications

(27 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recent solutions are indicated in Tang et al ( 2014 ) with the introduction of the portrait data, and in El Kababji and Srikantha ( 2020 ), among which the Generative Adversarial Networks together with a kernel density estimator are run on individual appliances. The various steps of data pre-processing can be combined a comprehensive approach that includes time synchronisation, noise cleansing, missing data imputation and performance assessment (Martinez-Luengo et al, 2019 ).…”

Section: Data Qualitymentioning

confidence: 99%

Data Consistency for Data-Driven Smart Energy Assessment

Chicco

2021

Front. Big Data

View full text Add to dashboard Cite

In the smart grid era, the number of data available for different applications has increased considerably. However, data could not perfectly represent the phenomenon or process under analysis, so their usability requires a preliminary validation carried out by experts of the specific domain. The process of data gathering and transmission over the communication channels has to be verified to ensure that data are provided in a useful format, and that no external effect has impacted on the correct data to be received. Consistency of the data coming from different sources (in terms of timings and data resolution) has to be ensured and managed appropriately. Suitable procedures are needed for transforming data into knowledge in an effective way. This contribution addresses the previous aspects by highlighting a number of potential issues and the solutions in place in different power and energy system, including the generation, grid and user sides. Recent references, as well as selected historical references, are listed to support the illustration of the conceptual aspects.

show abstract

Section: Data Qualitymentioning

confidence: 99%

Data Consistency for Data-Driven Smart Energy Assessment

Chicco

2021

Front. Big Data

View full text Add to dashboard Cite

show abstract

“…The way SHMS are designed and implemented follows the Statistical Pattern Recognition (SPR) paradigm, which is widely used across different industries for the implementation of damage detection strategies [35,36]. This paradigm was initially introduced in the SHM field by Farrar and Sohn [37] and later on adapted to the offshore wind industry by Martinez-Luengo et al [38,39]. The SPR paradigm consists of four stages, which are intensively described in [38].…”

Section: Shm Strategymentioning

confidence: 99%

“…Ideally all turbines (or as many as possible) should have the same SHMS or CMS installed so that conclusions and trends can be derived across the WF [39]. These SHMS or CMS must be reliable and have a relatively high service life.…”

mentioning

confidence: 99%

Guidelines and Cost-Benefit Analysis of the Structural Health Monitoring Implementation in Offshore Wind Turbine Support Structures

Martínez-Luengo

Shafiee

2019

Energies

Self Cite

View full text Add to dashboard Cite

This paper investigates how the implementation of Structural Health Monitoring Systems (SHMS) in the support structure (SS) of offshore wind turbines (OWT) affects capital expenditure (CAPEX) and operational expenditure (OPEX) of offshore wind farms (WF). In order to determine the added value of Structural Health Monitoring (SHM), the balance between the reduction in OPEX and the increase in CAPEX is evaluated. In this paper, guidelines for SHM implementation in offshore WF are developed and applied to a baseline scenario. The application of these guidelines consist of a review of present regulations in the United Kingdom and Germany, the development of SHM strategy, where the first stage of the Statistical Pattern Recognition (SPR) paradigm is explored, failure modes that can be monitored are identified, and SHM technologies and sensor distributions within the turbines are described for a baseline scenario. Furthermore, an inspection strategy where the different structural inspections to be carried out above and below water is also developed, together with an inspection plan for the lifetime of the structures, for the aforementioned baseline scenario. Once the guidelines have been followed and the SHM and inspection strategies developed, a cost-benefit analysis is performed on the baseline case (10% instrumented assets) and three other scenarios with 20%, 30% and 50% of instrumented assets. Finally, a sensitivity analysis is conducted to evaluate the effects of SHM hardware cost and the time spent in completing the inspections on OPEX and CAPEX of the WF. The results show that SHM hardware cost increases CAPEX significantly, however this increase is much lower than the reduction in OPEX caused by SHM. The results also show that an increase in the percentage of instrumented assets will reduce OPEX and this reduction is considerably higher than the cost of SHM implementation.

show abstract

“…The impact of missing data on monthly and annual average measurements was discussed for wind energy resource assessments [6] along with the corresponding impact on revenue [7]. Other applications include power curve estimation [8], wind farm control [9] and fatigue assessment [10].…”

Section: Introductionmentioning

confidence: 99%

Missing data in wind farm time series: Properties and effect on forecasts

Tawn

Browell

Dinwoodie³

2020

Electric Power Systems Research

View full text Add to dashboard Cite

Missing or corrupt data is common in real-world datasets; this affects the estimation and operation of analytical models where completeness is assumed or required. Statistical wind power forecasts utilise recent turbine data as model inputs, and must therefore be robust to missing data. We find that wind power data is 'missing not at random', with missing patterns also related to the forecast output. Approaches for dealing with this missing data in training and operation are proposed and evaluated through a case study, leading to a suggested forecasting methodology in the presence of missing data. In the training set, missing data was found to have significant negative impact on performance if simply omitted but this can be almost completely mitigated using multiple imputation. Greater increase in forecast errors is seen when input data are missing operationally, and retraining forecast models using the remaining inputs is found to be preferable to imputation.

show abstract

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

Cited by 53 publications

References 26 publications

Data Consistency for Data-Driven Smart Energy Assessment

Data Consistency for Data-Driven Smart Energy Assessment

Guidelines and Cost-Benefit Analysis of the Structural Health Monitoring Implementation in Offshore Wind Turbine Support Structures

Missing data in wind farm time series: Properties and effect on forecasts

Contact Info

Product

Resources

About