Failure Diagnosis of Wind Turbine Bearing Using Feature Extraction and a Neuro-Fuzzy Inference System (ANFIS)

Kordestani, Mojtaba; Rezamand, Milad; Carriveau, Rupp; Ting, David S.‐K.; Saif, Mehrdad

doi:10.1007/978-3-030-20521-8_45

Cited by 18 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the essential steps in CM systems to detect and isolate the type of failures is Fault Detection and Diagnosis (FDD). FDD approaches can be divided into three categories: (1) model-based methods; (2) data-driven methods; (3) knowledge-based methods (Hu et al, 2016; Kordestani et al, 2019). These three approaches in first approximation can be considered separate, although some attempts at employing a mixture of them are being formulated: for example, in Corley et al (2021) a combination of thermal modelling and data-driven methods is used for diagnosing gearbox faults based on drivetrain temperature data.…”

Section: Importance Of Condition and Performance Monitoring In Wtsmentioning

confidence: 99%

SCADA data for wind turbine data-driven condition/performance monitoring: A review on state-of-art, challenges and future trends

et al. 2022

View full text Add to dashboard Cite

This paper reviews the recent advancement made in data-driven technologies based on SCADA data for improving wind turbines’ operation and maintenance activities (e.g. condition monitoring, decision support, critical components failure detections) and the challenges associated with them. Machine learning techniques applied to wind turbines’ operation and maintenance (O&M) are reviewed. The data sources, feature engineering and model selection (classification, regression) and validation are all used to categorise these data-driven models. Our findings suggest that (a) most models use 10-minute mean SCADA data, though the use of high-resolution data has shown greater advantages as compared to 10-minute mean value but comes with high computational challenges. (b) Most of SCADA data are confidential and not available in the public domain which slows down technological advancements. (c) These datasets are used for both, the classification and regression of wind turbines but are used in classification extensively. And, (d) most commonly used data-driven models are neural networks, support vector machines, probabilistic models and decision trees and each of these models has its own merits and demerits. We conclude the paper by discussing the potential areas where SCADA data-based data-driven methodologies could be used in future wind energy research.

show abstract

Section: Importance Of Condition and Performance Monitoring In Wtsmentioning

confidence: 99%

SCADA data for wind turbine data-driven condition/performance monitoring: A review on state-of-art, challenges and future trends

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Fusion techniques are often categorized into three groups: 1) probabilistic-based fusion methods such as Bayesian reasoning methods [7]- [11], robust statistics methods [12], [13] 2) intelligent-based fusion methods like neural networks [14]- [19], Fuzzy logic [20]- [23], and 3) least square-based fusion methods such as Kalman filtering [24], [25] and OWA operator [26]- [29].…”

Section: A Literature Reviewmentioning

confidence: 99%

A New Fusion Estimation Method for Multi-Rate Multi-Sensor Systems With Missing Measurements

et al. 2020

Self Cite

View full text Add to dashboard Cite

A new fusion strategy is introduced in this article to estimate state for multi-rate multisensor systems with missing measurements. N sensors, which possess various sampling rates, render the measurements. Missing measurements with a certain probability pattern are also investigated. For these types of systems, Multi-rate Kalman filters are designed to estimate a target position at various sampling rates. Next, Ordered Weighted Averaging (OWA) operator is utilized to integrate multi-rate Kalman filters and improve the estimation quality. A new fusion strategy based on a real covariance matrix is introduced for updating the weighting factors, and proof of convergence is granted. Simulation studies on a tracking system verify the superior performance of the proposed fusion strategy in comparison with the Kalman filter, the multi-rate Kalman filters, and also the previous fusion methodology. INDEX TERMS Multi-rate Kalman filter, estimation, sensor data fusion, missing measurements, OWA operator.

show abstract

“…Because wind turbines convert mechanical energy into electrical energy, they have many moving parts. Most failures from wind turbines occur in the bearing structure [5]. Apart from that, wind energy is not always accessible like solar energy.…”

Section: Introductionmentioning

confidence: 99%

Anfis-Based Real-Time Power Estimation for Wind Turbines

Gökkuş

2023

Konya Journal of Engineering Sciences

View full text Add to dashboard Cite

In this study, it is aimed to make real-time power estimation for the V44-600 model wind turbine of Vestas company. The scope of the study is aimed to perform ANFIS-based power estimation for the V44-600 VESTAS wind turbine, which is intensely used in the wind industry, by using the wind speed and air density data of the city of Nevşehir. For this purpose, an Adaptive Network Based Fuzzy Inference System (ANFIS) trained on V44-600 wind turbine data was used. For the training and testing steps of ANFIS, wind speed, air density, and output power of the wind turbine are used as input-output parameters. As a result of the simulations and training, the percent relative error value in the widest range where the prediction value deviates from the true value is 11.86%. This value was higher than expected due to the scarcity of the data used in the ANFIS training (144) and the repetitive values in the output power. Similarly, the lowest efficiency value is 89.4%. Despite all this, it has been observed that ANFIS gives good results if the data used in the testing process is within the scope of the data used in the training. Moreover, the developed model when supported with 32-bit hardware can make real-time power estimation for a real wind turbine. The main motivation for this study; is develop a model that can predict the output power for the Vestas V44-600 model based on wind speed and air density data. In addition, it is to produce the Fuzzy Interface System (FIS) file that enables the developed model to run on embedded systems.

show abstract

Failure Diagnosis of Wind Turbine Bearing Using Feature Extraction and a Neuro-Fuzzy Inference System (ANFIS)

Cited by 18 publications

References 18 publications

SCADA data for wind turbine data-driven condition/performance monitoring: A review on state-of-art, challenges and future trends

SCADA data for wind turbine data-driven condition/performance monitoring: A review on state-of-art, challenges and future trends

A New Fusion Estimation Method for Multi-Rate Multi-Sensor Systems With Missing Measurements

Anfis-Based Real-Time Power Estimation for Wind Turbines

Contact Info

Product

Resources

About