Wind Turbine Condition Monitoring Strategy through Multiway PCA and Multivariate Inference

Pozo, Francesc; Vidal, Yolanda; Salgado, Óscar

doi:10.3390/en11040749

Cited by 51 publications

(49 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We consider two main reasons for the scaling or standardization of the raw data in matrix

boldX

in Equation (1): first, to process data with different magnitudes that come from different sensors and second, to simplify the computations of the data transformation in Section using PCA. How the raw data are scaled may severely affect the overall performance of the subsequent methods that have to be applied . Some strategies consider each column vector in matrix

boldX

as an independent entity, and each element in the column vector is normalized by subtracting the mean of all the elements in the column and by dividing by the standard deviation of the same set of data.…”

Section: Data Preprocessing and Clustering: Baseline Datamentioning

confidence: 99%

“…Therefore, in this case—that can be defined as column scaling —the mean of each column is zero and its standard deviation is one. A second strategy—the so‐called group scaling—considers the nature of the vertical blocks, where all measures come from the same sensor. In this case, each element in the block is normalized by subtracting the mean of all the elements in the block and by dividing by the standard deviation of the same set of data.…”

Section: Data Preprocessing and Clustering: Baseline Datamentioning

confidence: 99%

See 1 more Smart Citation

Vibration‐based detection and classification of structural changes using principal component analysis and ‐distributed stochastic neighbor embedding

Agis

Burgos

Pozo

2020

Struct Control Health Monit

Self Cite

View full text Add to dashboard Cite

Summary This paper describes a structural health monitoring strategy to detect and classify structural changes in structures that can be equipped with sensors. The proposed approach is based on the t‐distributed stochastic neighbor embedding ( t‐SNE), a nonlinear technique that can represent the local structure of high‐dimensional data collected from multiple sensors in a plane or spatial representation. We propose the following basic steps for the detection and classification. First, the raw data are preprocessed: We scale the data using the mean‐centered group scaling and apply principal component analysis to reduce the dimensionality of the scaled data. Second, t‐SNE is applied to represent the scaled and reduced data as points in a plane, defining a cluster for each structural state. Finally, the current structure to be diagnosed is associated with a cluster (or structural state) using three different strategies: (a) the smallest point‐centroid distance; (b) the majority voting; and (c) the sum of the inverse distances. The combination of t‐SNE with our preprocessing and the three proposed classification strategies significantly improves the quality of the clusters that represent different structural states. We evaluate the performance of our method using experimental data from an aluminum plate instrumented with piezoelectric transducers. Results are presented in the time domain, and they reveal the high classification accuracy and strong performance of this method, with a percentage of correct decisions close to 100% in several scenarios.

show abstract

“…We consider two main reasons for the scaling or standardization of the raw data in matrix

boldX

boldX

Section: Data Preprocessing and Clustering: Baseline Datamentioning

confidence: 99%

Section: Data Preprocessing and Clustering: Baseline Datamentioning

confidence: 99%

Vibration‐based detection and classification of structural changes using principal component analysis and ‐distributed stochastic neighbor embedding

Agis

Burgos

Pozo

2020

Struct Control Health Monit

Self Cite

View full text Add to dashboard Cite

show abstract

“…Matrix X in Equation (3) is rescaled through MCGS [21] because of the different magnitudes and scales in the measurements.…”

Section: Data Integration: Unfolding and Scalingmentioning

confidence: 99%

“…The second step, before data transformation, is the data normalization. We perform the mean-centered group scaling (MCGS), as detailed in [21]. 3.…”

Section: Introductionmentioning

confidence: 99%

Vibration-Based Structural Health Monitoring Using Piezoelectric Transducers and Parametric t-SNE

Agis¹,

Pozo²

2020

Sensors

Self Cite

View full text Add to dashboard Cite

In this paper, we evaluate the performance of the so-called parametric t-distributed stochastic neighbor embedding (P-t-SNE), comparing it to the performance of the t-SNE, the non-parametric version. The methodology used in this study is introduced for the detection and classification of structural changes in the field of structural health monitoring. This method is based on the combination of principal component analysis (PCA) and P-t-SNE, and it is applied to an experimental case study of an aluminum plate with four piezoelectric transducers. The basic steps of the detection and classification process are: (i) the raw data are scaled using mean-centered group scaling and then PCA is applied to reduce its dimensionality; (ii) P-t-SNE is applied to represent the scaled and reduced data as 2-dimensional points, defining a cluster for each structural state; and (iii) the current structure to be diagnosed is associated with a cluster employing two strategies: (a) majority voting; and (b) the sum of the inverse distances. The results in the frequency domain manifest the strong performance of P-t-SNE, which is comparable to the performance of t-SNE but outperforms t-SNE in terms of computational cost and runtime. When the method is based on P-t-SNE, the overall accuracy fluctuates between 99.5% and 99.75%.

show abstract

“…In this scenario, the use of SCADA data is gaining importance [14]. SCADA-data based methods can also be implemented in real-time condition monitoring of WTs [15,16].…”

Section: Introductionmentioning

confidence: 99%

Current Signature and Vibration Analyses to Diagnose an In-Service Wind Turbine Drive Train

Artigao

Koukoura

Carroll³

et al. 2018

Energies

View full text Add to dashboard Cite

Abstract:The goal of the present paper is to achieve the diagnosis of an in-service 1.5 MW wind turbine equipped with a doubly-fed induction generator through current signature and vibration analyses. Real data from operating machines have rarely been analysed in the scientific literature through current signature analysis supported by vibrations. The wind turbine under study was originally misdiagnosed by the operator, where a healthy component was replaced and the actual failure continued progressing. The chronological evolution of both the electrical current and vibration spectra is presented to conduct an in-depth tracking of the fault. The diagnosis is achieved through spectral analysis of the stator currents, where fault frequency components related to rotor mechanical unbalance are identified. This is confirmed by the vibration analysis, which provides insightful information on the health of the drive train. These results can be implemented in condition monitoring strategies, which is of great interest to optimise operation and maintenance costs of wind farms.

show abstract

Wind Turbine Condition Monitoring Strategy through Multiway PCA and Multivariate Inference

Cited by 51 publications

References 34 publications

Vibration‐based detection and classification of structural changes using principal component analysis and ‐distributed stochastic neighbor embedding

Vibration‐based detection and classification of structural changes using principal component analysis and ‐distributed stochastic neighbor embedding

Vibration-Based Structural Health Monitoring Using Piezoelectric Transducers and Parametric t-SNE

Current Signature and Vibration Analyses to Diagnose an In-Service Wind Turbine Drive Train

Contact Info

Product

Resources

About