Journal article
Virtual Wind Speed Sensor for Wind Turbines
Journal of energy engineering, Vol.137(2), pp.59-69
06/01/2011
DOI: 10.1061/(ASCE)EY.1943-7897.0000035
Abstract
A data-driven approach for development of a virtual wind-speed sensor for wind turbines is presented. The virtual wind-speed sensor is built from historical wind-farm data by data-mining algorithms. Four different data-mining algorithms are used to develop models using wind-speed data collected by anemometers of various wind turbines on a wind farm. The computational results produced by different algorithms are discussed. The neural network (NN) with the multilayer perceptron (MLP) algorithm produced the most accurate wind-speed prediction among all the algorithms tested. Wavelets are employed to denoise the high-frequency wind-speed data measured by anemometers. The models built with data-mining algorithms on the basis of the wavelet-transformed data are to serve as virtual wind-speed sensors for wind turbines. The wind speed generated by a virtual sensor can be used for different purposes, including online monitoring and calibration of the wind-speed sensors, as well as providing reliable wind-speed input to a turbine controller. The approach presented in this paper is applicable to utility-scale wind turbines of any type.
Details
- Title: Subtitle
- Virtual Wind Speed Sensor for Wind Turbines
- Creators
- Andrew Kusiak - Univ. of Iowa Dept. of Mechanical and Industrial Engineering, 3131 Seamans Center, , Iowa City, IA 52242-1527 (corresponding author). E-mailHaiyang Zheng - Univ. of Iowa Dept. of Mechanical and Industrial Engineering, 3131 Seamans Center, , Iowa City, IA 52242-1527Zijun Zhang - Univ. of Iowa Dept. of Mechanical and Industrial Engineering, 3131 Seamans Center, , Iowa City, IA 52242-1527
- Resource Type
- Journal article
- Publication Details
- Journal of energy engineering, Vol.137(2), pp.59-69
- Publisher
- American Society of Civil Engineers
- DOI
- 10.1061/(ASCE)EY.1943-7897.0000035
- ISSN
- 0733-9402
- eISSN
- 1943-7897
- Language
- English
- Date published
- 06/01/2011
- Academic Unit
- Nursing; Industrial and Systems Engineering
- Record Identifier
- 9984064255202771
Metrics
14 Record Views