Identifying Health Status of Wind Turbines by Using Self Organizing Maps and Interpretation-Oriented Post-Processing Tools

Blanco-M, Alejandro; Gibert, Karina; Martí-Puig, Pere; Cusidó, J.; Solé-Casals, Jordi

doi:10.3390/en11040723

Cited by 29 publications

(24 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To determine the origin, they compute a statistic of which variable has had the greatest contribution to generate the distance from the BMU. Following with the SOM techniques, authors such as Blanco-M. et al [39] propose a process that includes a clustering technique on the result of the turbines after applying SOM, in order to identify the health status of the turbines. Other authors, such as Leahy et al [40], focus on clustering groups of alarms, detecting particular sequences before a failure.…”

Section: Introductionmentioning

confidence: 99%

Feature Selection Algorithms for Wind Turbine Failure Prediction

Martí-Puig

Blanco-M

Cárdenas³

et al. 2019

Energies

Self Cite

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

Section: Introductionmentioning

confidence: 99%

Feature Selection Algorithms for Wind Turbine Failure Prediction

Martí-Puig

Blanco-M

Cárdenas³

et al. 2019

Energies

Self Cite

View full text Add to dashboard Cite

show abstract

“…Data Science (DS) is an emergent research field that helps better understand the complex mechanisms behind environmental phenomena. In Gibert et al (2018) an overview of what can be called the field of Environmental Data Science is provided. The paper describes the DS process, and the role of Data Mining (DM) methods, which is identified as one of the most critical to transform data into added value and new knowledge for ESs.…”

Section: Introductionmentioning

confidence: 99%

“…In Gibert et al (2018), the main challenges of Environmental Data Science are identified and discussed to promote research in the area. One of these main challenges is the lack of guidance in choosing the right analytics method for a given problem.…”

Section: Introductionmentioning

confidence: 99%

Which method to use? An assessment of data mining methods in Environmental Data Science

Gibert

Izquierdo

Sànchez–Marrè

et al. 2018

Environmental Modelling & Software

Self Cite

View full text Add to dashboard Cite

Data Mining (DM) is a fundamental component of the Data Science process. Over recent years a huge library of DM algorithms has been developed to tackle a variety of problems in fields such as medical imaging and traffic analysis. Many DM techniques are far more flexible than more classical numerial simulation or statistical modelling approaches. These could be usefully applied to data-rich environmental problems. Certain techniques such as artificial neural networks, clustering, case-based reasoning or Bayesian networks have been applied in environmental modelling, while other methods, like support vector machines among others, have yet to be taken up on a wide scale. There is greater scope for many lesser known techniques to be applied in environmental research, with the potential to contribute to addressing some of the current open environmental challenges. However, selecting the best DM technique for a given environmental problem is not a simple decision, and there is a lack of guidelines and criteria that helps the data scientist and environmental scientists to ensure effective knowledge extraction from data. This paper provides a broad introduction to the use of DM in Data Science processes for environmental researchers. Data Science contains three main steps (pre-processing, data mining and post-processing). This paper provides a conceptualization of Environmental Systems and a conceptualization of DM methods, which are in the core step of the Data Science process. These two elements define a conceptual framework that is on the basis of a new methodology proposed for relating the characteristics of a given environmental problem with a family of Data Mining methods. The paper provides a general overview and guidelines of DM techniques to a non-expert user, who can decide with this support which is the more suitable technique to solve their problem at hand. The decision is related to the bidimensional relationship between the type of environmental system and the type of DM method. An illustrative two way table containing references for each pair Environmental System-Data Mining method is presented and discussed. Some examples of how the proposed methodology is used to support DM method selection are also presented, and challenges and future trends are identified.

show abstract

“…They suggest using cumulative particle counts to better detect failures instead of direct particle creation measurements and to combine various sensors in order to improve confidence in the diagnosis. In the work by the authors of [23], they create a health indicator based on the centroids proposed by a Self Organising Map in order to group WTs according to health status using SCADA data. This way operators are given additional information regarding the health state of the WTs, and can plan consequently.…”

mentioning

confidence: 99%

A Context-Aware Oil Debris-Based Health Indicator for Wind Turbine Gearbox Condition Monitoring

et al. 2019

View full text Add to dashboard Cite

One of the greatest challenges of optimising the correct operation of wind turbines is detecting the health status of their core components, such as gearboxes in particular. Gearbox monitoring is a widely studied topic in the literature, nevertheless, studies showing data of in-service wind turbines are less frequent and tend to present difficulties that are otherwise overlooked in test rig based works. This work presents the data of three wind turbines that have gearboxes in different damage stages. Besides including the data of the SCADA (Supervisory Control And Signal Acquisition) system, additional measurements of online optical oil debris sensors are also included. In addition to an analysis of the behaviour of particle generation in the turbines, a methodology to identify regimes of operation with lower variation is presented. These regimes are later utilised to develop a health index that considers operation states and provides valuable information regarding the state of the gearboxes. The proposed health index allows distinguishing damage severity between wind turbines as well as tracking the evolution of the damage over time.

show abstract

Identifying Health Status of Wind Turbines by Using Self Organizing Maps and Interpretation-Oriented Post-Processing Tools

Cited by 29 publications

References 34 publications

Feature Selection Algorithms for Wind Turbine Failure Prediction

Feature Selection Algorithms for Wind Turbine Failure Prediction

Which method to use? An assessment of data mining methods in Environmental Data Science

A Context-Aware Oil Debris-Based Health Indicator for Wind Turbine Gearbox Condition Monitoring

Contact Info

Product

Resources

About