SCADA data based condition monitoring of wind turbines

“…Methods of fault diagnostics for wind turbines controlled by SCADA are examined in work [8]. The authors provide a review of a number of diagnostic methods, including methods based on artificial neural networks, fuzzy-logic methods, and combined methods such as adaptive neuro-fuzzy inference.…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

Evaluation to determine the efficiency for the diagnosis search formation method of failures in automated systems

Syrotkina

Alekseyev

Aleksieiev

2017

EEJET

View full text Add to dashboard Cite

show abstract

“…In many papers of the state of the art research we can see that the selection of the variables is done manually by an expert, or based on the perception of the author according to the subsystem to analyze. Some authors, such as [29,33,42,43], include some type of reduction stage by correlations or PCA, but do not make a comparison of selection methods, or this comparison does not contain methods that include the interaction of more than two variables such as those presented in this paper.…”

Section: Introductionmentioning

confidence: 99%

Feature Selection Algorithms for Wind Turbine Failure Prediction

Martí-Puig

Blanco-M

Cárdenas³

et al. 2019

Energies

View full text Add to dashboard Cite

It is well known that each year the wind sector has profit losses due to wind turbine failures and operation and maintenance costs. Therefore, operations related to these actions are crucial for wind farm operators and linked companies. One of the key points for failure prediction on wind turbine using SCADA data is to select the optimal or near optimal set of inputs that can feed the failure prediction (prognosis) algorithm. Due to a high number of possible predictors (from tens to hundreds), the optimal set of inputs obtained by exhaustive-search algorithms is not viable in the majority of cases. In order to tackle this issue, show the viability of prognosis and select the best set of variables from more than 200 analogous variables recorded at intervals of 5 or 10 min by the wind farm’s SCADA, in this paper a thorough study of automatic input selection algorithms for wind turbine failure prediction is presented and an exhaustive-search-based quasi-optimal (QO) algorithm, which has been used as a reference, is proposed. In order to evaluate the performance, a k-NN classification algorithm is used. Results showed that the best automatic feature selection method in our case-study is the conditional mutual information (CMI), while the worst one is the mutual information feature selection (MIFS). Furthermore, the effect of the number of neighbours (k) is tested. Experiments demonstrate that k = 1 is the best option if the number of features is higher than 3. The experiments carried out in this work have been extracted from measures taken along an entire year and corresponding to gearbox and transmission systems of Fuhrländer wind turbines.

show abstract

“…The conditionmonitoring approach based on SCADA datasets is cost-efficient and readily available. [26][27][28] The research and application of other important parameters, based on WT condition monitoring, for example, temperature-related parameters, are mainly dependent on SCADA data. Feng et al 29 showed that the gearbox temperature rises when the gearbox efficiency decreases.…”

Section: Introductionmentioning

confidence: 99%

Condition monitoring of wind turbines based on analysis of temperature-related parameters in supervisory control and data acquisition data

Xian

Zhao

Yang

et al. 2019

Measurement and Control

View full text Add to dashboard Cite

In order to conduct a further in-depth exploration of the role of temperature-related parameters in the condition monitoring of wind turbines, this paper proposes a method to assess the condition of wind turbines by analyzing the supervisory control and data acquisition system temperature-related parameters based on existing research. A prediction model of time-sequence regression is established, based on the key temperature signals of WTs, so as to reflect their health condition in the form of prediction residuals. A kind of health index from the perspective of temperature-related parameters is developed by separating the statistics concerning the conformity of the predicted values of key temperature parameters within a certain time window from the measured values in order to clearly present the implied information on the health condition of wind turbines contained in the model prediction residuals. The case study shows that the trend of health index from the perspective of temperature-related parameters is consistent with the health condition of wind turbines. In some instances, its decline obviously occurs earlier than the maintenance provided to address the stoppage, suggesting that such indexes can effectively reflect some early health problems of the wind turbines to provide a reference for their scientific maintenance.

show abstract

SCADA data based condition monitoring of wind turbines

Cited by 64 publications

References 29 publications

Evaluation to determine the efficiency for the diagnosis search formation method of failures in automated systems

Evaluation to determine the efficiency for the diagnosis search formation method of failures in automated systems

Feature Selection Algorithms for Wind Turbine Failure Prediction

Condition monitoring of wind turbines based on analysis of temperature-related parameters in supervisory control and data acquisition data

Contact Info

Product

Resources

About