On the Selection of Input Variables for a Wind Turbine Load Monitoring System

Vera-Tudela, Luis; Kühn, Martin

doi:10.1016/j.protcy.2014.09.045

Cited by 18 publications

(14 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to DEL, load distributions (which represent the occurrence probability of load cycles or exposure time of each load magnitude) are also estimated. The work done in Vera‐Tudela and Kühn contains a comparison between different input selection methods for an ANNs‐based load estimation model.…”

Section: State Of the Artmentioning

confidence: 99%

“…In line with Cosack and Vera‐Tudela and Kühn, our investigation considers ANNs as nonlinear estimation models. While the implementation of ANNs in the cited works is proper, we perform deeper research on the procedures for an automatic optimal input selection and the design of the most suitable configuration of the ANNs.…”

Section: State Of the Artmentioning

confidence: 99%

“…Other authors have accomplished analogous tasks before. Special attention deserves, where a methodology particularly developed for WT load estimation problems is described. Three different techniques are commonly used in the literature as input selection procedures: Filter.…”

Section: Dimensionality Reductionmentioning

confidence: 99%

See 2 more Smart Citations

Modelling damage equivalent loads in wind turbines from general operational signals: Exploration of relevant input selection methods using aeroelastic simulations

et al. 2018

View full text Add to dashboard Cite

Fatigue represents a critical issue in many structural applications, and wind turbines are not an exception. Their dynamic response over the years determines the turbine's lifespan, meaning that fatigue loads have a clear impact on the Cost of Energy. Since the direct experimental determination of the loading state is complex or expensive, estimations arising from general operational signals can be explored as an indirect way to acquire knowledge of fatigue loading levels.A case study based on 10-minute aeroelastic simulations of a wind turbine dynamics is used to develop a Damage Equivalent Load estimation model using operational signals (typically recorded by SCADA systems) as inputs. The focus is on both the input selection and the model configuration, seeking the combination which reaches the lowest error. Three filters and two innovative wrappers (exploration and optimization) were considered within the selection. Linear and Artificial Neural Network models were implemented and compared. Results showed performances in Damage Equivalent Load estimation below 4% in terms of Normalized Root Mean Squared Error, which is promising as compared with related work. Additional conclusions were obtained concerning appropriate Artificial Neural Network configurations (net type, architecture and training algorithm), likewise the potential contribution of a proposed genetic algorithm.

show abstract

Section: State Of the Artmentioning

confidence: 99%

Section: State Of the Artmentioning

confidence: 99%

See 1 more Smart Citation

Modelling damage equivalent loads in wind turbines from general operational signals: Exploration of relevant input selection methods using aeroelastic simulations

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Optimal selection of inputs using PCA to develop predictive models of different industrial applications is reported in Refs. [26,27].…”

Section: Literature Surveymentioning

confidence: 99%

Hourly prediction of a building's electricity consumption using case-based reasoning, artificial neural networks and principal component analysis

Platon

Dehkordi

Martel

2015

Energy and Buildings

168

View full text Add to dashboard Cite

“…According to [24] those conditions are not representative with respect to the dynamics, concerning in detail the load situation or related real conditions. Some contributions [25] state that certainly measured signals from WT system such as generated power, pitch angles, generator speed can also be used to perform the fatigue load analysis as those parameters are affected by structural loads. In this case, the significance of other parameters that may also be used is not clarified and suitably inferred [25].…”

Section: Effect Of Inflow Conditions On Wt Fatigue Growth and Modelingmentioning

confidence: 99%

Structural health management utilization for lifetime prognosis and advanced control strategy deployment of wind turbines: An overview and outlook concerning actual methods, tools, and obtained results

Beganović

Söffker

2016

Renewable and Sustainable Energy Reviews

View full text Add to dashboard Cite

On the Selection of Input Variables for a Wind Turbine Load Monitoring System

Cited by 18 publications

References 6 publications

Modelling damage equivalent loads in wind turbines from general operational signals: Exploration of relevant input selection methods using aeroelastic simulations

Modelling damage equivalent loads in wind turbines from general operational signals: Exploration of relevant input selection methods using aeroelastic simulations

Hourly prediction of a building's electricity consumption using case-based reasoning, artificial neural networks and principal component analysis

Structural health management utilization for lifetime prognosis and advanced control strategy deployment of wind turbines: An overview and outlook concerning actual methods, tools, and obtained results

Contact Info

Product

Resources

About