Nonlinear system identification for model-based condition monitoring of wind turbines |
| |
| Affiliation: | 1. Stichting Monitoring Zonnestroom (SMZ), Utrecht, The Netherlands;2. Utrecht University, CopernicusInstitute, Utrecht, The Netherlands;3. New-Energy-Works (NEW), Utrecht, The Netherlands;4. Rencom, Ouderkerk a/d Amstel, The Netherlands;5. Holland Solar, Utrecht, The Netherlands;6. Organisatie voor Duurzame Energie (ODE), Utrecht, The Netherlands;1. Cascadia Coast Research Ltd., 26 Bastion Square, Third Floor – Burnes House, Victoria, BC V8W1H9, Canada;2. University of Victoria, Department of Mechanical Engineering, PO Box 3075 STN CSC, Victoria, BC V8W 3P6, Canada;1. School of Advanced Materials Engineering, Kookmin University, Seoul 136-702, South Korea;2. Department of Chemistry, University of Dhaka, Dhaka 1000, Bangladesh;1. EDMANS Group, Department of Mechanical Engineering, University of La Rioja, Logroño, Spain;2. Division of Biosciences, University of Helsinki, 00014 Helsinki, Finland;3. Electrical Engineering Department, EUITI-UPM, Ronda de Valencia 3, 28012 Madrid, Spain;4. Instituto de Energía Solar, Ciudad Universitaria s/n, Madrid, Spain;5. Renewable Energy Division (Energy Department), CIEMAT Avda. Complutense 22, 28040 Madrid, Spain |
| |
| Abstract: | This paper proposes a data driven model-based condition monitoring scheme that is applied to wind turbines. The scheme is based upon a non-linear data-based modelling approach in which the model parameters vary as functions of the system variables. The model structure and parameters are identified directly from the input and output data of the process. The proposed method is demonstrated with data obtained from a simulation of a grid-connected wind turbine where it is used to detect grid and power electronic faults. The method is evaluated further with SCADA data obtained from an operational wind farm where it is employed to identify gearbox and generator faults. In contrast to artificial intelligence methods, such as artificial neural network-based models, the method employed in this paper provides a parametrically efficient representation of non-linear processes. Consequently, it is relatively straightforward to implement the proposed model-based method on-line using a field-programmable gate array. |
| |
| Keywords: | Distributed generation (DG) Wind turbine Condition monitoring (CM) Fault detection Modelling and simulation SCADA data |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
