Support Vector Machine and K-fold Cross-validation to Detect False Alarms in Wind Turbines

Ana Maria Peco Chacon () and Fausto Pedro García Márquez ()
Additional contact information
Ana Maria Peco Chacon: Universidad Castilla-La Mancha
Fausto Pedro García Márquez: Universidad Castilla-La Mancha

A chapter in Sustainability, 2023, pp 81-97 from Springer

Abstract: Abstract Wind energy is a growing market, due to improved monitoring systems, decreased downtime, and optimal predictive maintenance. Classification algorithms based on machine learning efficiently categorize large volumes of complex data. K-Fold cross-validation is a competent tool for measuring the success rate of classification algorithms. The purpose of this research is to compare the performance of various kernel functions for the support vector machine algorithm, as well as to analyze the different values of K-fold cross-validation and holdout validation. The approach is applied to a real dataset of wind turbine, with the aim to detect false alarms. The results indicate an accuracy of 99.2%, and the F1 is 0.996. These values indicate that the methodology proposed is efficient to detect and identify false alarms.

Keywords: Wind turbine; Maintenance management; SCADA; False alarm; Support vector machine; Accuracy; Prediction model; Cross-validation (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:isochp:978-3-031-16620-4_6

Ordering information: This item can be ordered from
http://www.springer.com/9783031166204

DOI: 10.1007/978-3-031-16620-4_6

Access Statistics for this chapter

More chapters in International Series in Operations Research & Management Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().