Effects of the pre-processing algorithms in fault diagnosis of wind turbines. (December 2018)

• Record Type: Journal Article
• Authors: Marti-Puig, Pere; Blanco-M, Alejandro; Cárdenas, Juan José; Cusidó, Jordi; Solé-Casals, Jordi
• Is Part Of: Environmental modelling & software. Volume 110(2018)
• Page Start: 119
• Page End: 128
• Publication Date: 2018-12
• Subjects: Wind farms -- SCADA data -- Pre-processing -- Outliers -- Fault diagnosis -- Renewable energy; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2018.05.002
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: The wind sectors pends roughly 2200M€ in repair the wind turbines failures. These failures do not contribute to the goal of reducing greenhouse gases emissions. The 25–35% of the generation costs are operation and maintenance services. To reduce this amount, the wind turbine industry is backing on the Machine Learning techniques over SCADA data. This data can contain errors produced by missing entries, uncalibrated sensors or human errors. Each kind of error must be handled carefully because extreme values are not always produced by data reading errors or noise. This document evaluates the impact of removing extreme values (outliers) applying several widely used techniques like Quantile, Hampel and ESD with the recommended cut-off values. Experimental results on real data show that removing outliers systematically is not a good practice. The use of manually defined ranges (static and dynamic) could be a better filtering strategy. Highlights: To reduce generation costs in wind farms, machine learning techniques over SCADA data can be used. We evaluate the impact of removing extreme values of the data, applying widely used techniques. Experimental results on real data show that removing outliers systematically is not a good practice. The use of manual defined ranges (static and dynamic) could be a better filtering strategy. Using this strategy the models contain more information about failure patterns.