Ice Detection for Wind Turbine Blades Based on PSO-SVM Method
Authors:
Open Access
- 1 September 2018
- conference paper
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1087 (2) , 022036
Abstract
Detection of ice formation on wind turbine blades is still in the research and development stage. Generally,wind turbines have to be shut down to deice the blades when the icing is serious. This paper adopts a data-driven approach to detect the icing blades by analyzing a lot of actual wind field data collected by SCADA system to create a prediction model. Considering the characteristics of industrial big data, firstly, we preprocess the field data by eliminating the singular data, and then select suitable features through mechanism analysis. Finally, the characteristic data are fed into the support vector machine (SVM) which uses the particle swarm optimization (PSO) algorithm to optimize the parameters. Experimental results show that the proposed approach can achieve good performance and provide a new idea for fault diagnosis of ice formation on wind turbine blades.Keywords
This publication has 4 references indexed in Scilit:
- Ice detection using thermal infrared radiometry on wind turbine bladesMeasurement, 2016
- Ice detection on wind turbines using the observed power curveWind Energy, 2015
- A Review of the Effects of Ice Accretion on the Structural Behavior of Wind TurbinesWind Engineering, 2013
- Ice detection and classification on an aircraft wing with ultrasonic shear horizontal guided wavesIEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2009