Gaussian process models for mitigation of operational variability in the structural health monitoring of wind turbines

Avendaño-Valencia, Luis David; Chatzi, Eleni; Tcherniak, Dmitri

doi:10.1016/j.ymssp.2020.106686

Cited by 75 publications

(32 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It weights targets with respect to distance between training and test input to predict the output. In contrast to approaches mentioned, GPR is suitable for dealing with the RUL estimation issue of small data sets and multi-dimensional operating space [188]. Aye et al [189] used affine mean Gaussian process regression (AMGPR) to predict the RUL of slow speed bearing.…”

Section: Gaussian Process Regressionmentioning

confidence: 99%

Technology development and commercial applications of industrial fault diagnosis system: a review

Liu

Cichoń

Królczyk

et al. 2021

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Machinery will fail due to complex and tough working conditions. It is necessary to apply reliable monitoring technology to ensure their safe operation. Condition-based maintenance (CBM) has attracted significant interest from the research community in recent years. This paper provides a review on CBM of industrial machineries. Firstly, the development of fault diagnosis systems is introduced systematically. Then, the main types of data in the field of the fault diagnosis are summarized. After that, the commonly used techniques for the signal processing, fault diagnosis, and remaining useful life (RUL) prediction are discussed, and the advantages and disadvantages of these existing techniques are explored for some specific applications. Typical fault diagnosis products developed by corporations and universities are surveyed. Lastly, discussions on current developing situation and possible future trends are in the CBM performed.

show abstract

Section: Gaussian Process Regressionmentioning

confidence: 99%

Technology development and commercial applications of industrial fault diagnosis system: a review

Liu

Cichoń

Królczyk

et al. 2021

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

“…The DT is calculated based on the observations considered for the learning. In the literature, there are some works about wind turbine blades in operation that investigate other techniques to mitigate environmental variations and operations (Avendaño-Valencia et al 2020;Movsessian et al 2020). One of the major challenges in regression problems for damage detection and quantification is the valid correlation of the parameters, the damaged area with the metric DI, which has sensitive features about severity.…”

Section: Introductionmentioning

confidence: 99%

Polynomial Chaos-Kriging metamodel for quantification of the debonding area in large wind turbine blades

Pavlack

Paixão

Silva

et al. 2021

Structural Health Monitoring

View full text Add to dashboard Cite

This study aims to investigate the performance of a data-driven methodology for quantifying damage based on the use of a metamodel obtained from the Polynomial Chaos-Kriging method. The investigation seeks to quantify the severity of the damage, described by a specific type of debonding in a wind turbine blade as a function of a damage index. The damage indexes used are computed using a data-driven vibration-based structural health monitoring methodology. The blade’s debonding damage is introduced artificially, and the blade is excited with an electromechanical actuator that introduces a mechanical impulse causing the impact on the blade. The acceleration responses’ vibrations are measured by accelerometers distributed along the trailing and the wind turbine blade. A metamodel is formerly obtained through the Polynomial Chaos-Kriging method based on the damage indexes, trained with the blade’s healthy condition and four damage conditions, and validated with the other two damage conditions. The Polynomial Chaos-Kriging manifests promising results for capturing the proper trend for the severity of the damage as a function of the damage index. This research complements the damage detection analyses previously performed on the same blade.

show abstract

“…In order to address the shortcomings mentioned above, this paper proposes a method of health assessment of hydropower units based on Gaussian process regression (GPR). GPR, as a new machine learning method based on Bayesian theory and statistical learning theory, has achieved good results in other fields of health monitoring [27][28][29]. Firstly, the paper uses the Pearson correlation coefficient (PCC), maximum information coefficient (MIC), and grey correlation degree (GCD) to select the appropriate operation state parameters from the massive data stored in the hydropower unit's system to construct the input eigenvector.…”

Section: Introductionmentioning

confidence: 99%

The Prediction Method on the Early Failure of Hydropower Units Based on Gaussian Process Regression Driven by Monitoring Data

et al. 2020

View full text Add to dashboard Cite

The hydropower units have a complex structure, complicated and changing working conditions, complexity and a diversity of faults. Effectively evaluating the healthy operation status and accurately predicting the failure for the hydropower units using the real-time monitoring data is still a difficult problem. To this end, this paper proposes a prediction method for the early failure of hydropower units based on Gaussian process regression (GPR). Firstly, by studying the correlation between different monitoring data, nine state parameters closely related to the operation of hydropower units are mined from the massive data. Secondly, a health evaluation model is established based on GPR using the historical multi-dimensional monitoring information and fault-free monitoring data at the initial stage of unit operation. Finally, a condition monitoring directive based on the Mahalanobis distance (MD) is designed. The effectiveness of the proposed method is verified by several typical examples of monitoring data of a hydropower station in Guangxi, China. The results show that, in three cases, the abnormal conditions of the unit are found 2 days, 4 days and 43 days earlier than those of regular maintenances respectively. Therefore, the method can effectively track the change process of the operation state of hydropower units, and detect the abnormal operation state of hydropower units in advance.

show abstract

Gaussian process models for mitigation of operational variability in the structural health monitoring of wind turbines

Cited by 75 publications

References 34 publications

Technology development and commercial applications of industrial fault diagnosis system: a review

Technology development and commercial applications of industrial fault diagnosis system: a review

Polynomial Chaos-Kriging metamodel for quantification of the debonding area in large wind turbine blades

The Prediction Method on the Early Failure of Hydropower Units Based on Gaussian Process Regression Driven by Monitoring Data

Contact Info

Product

Resources

About