Study on Parameters Modeling of Wind Turbines Using SCADA Data
نویسندگان
چکیده
Taking the advantage of the current massive monitoring data from Supervisory Control and Data Acquisition (SCADA) system of wind farm, it is of important significance for anomaly detection, early warning and fault diagnosis to build the data model of state parameters of wind turbines (WTs). The operational conditions and the relationships between the state parameters of wind turbines are complex. It is difficult to establish the model of state parameter accurately, and the modeling method of state parameters of wind turbines considering parameter selection is proposed. Firstly, by analyzing the characteristic of SCADA data, a reasonable range of data and monitoring parameters are chosen. Secondly, neural network algorithm is adapted, and the selection method of input parameters in the model is presented. Generator bearing temperature and cooling air temperature are regarded as target parameters, and the two models are built and input parameters of the models are selected, respectively. Finally, the parameter selection method in this paper and the method using genetic algorithm-partial least square (GA-PLS) are analyzed comparatively, and the results show that the proposed methods are correct and effective. Furthermore, the modeling of two parameters illustrate that the method in this paper can applied to other state parameters of wind turbines. Copyright © 2014 IFSA Publishing, S. L.
منابع مشابه
Condition Parameter Modeling for Anomaly Detection in Wind Turbines
Data collected from the supervisory control and data acquisition (SCADA) system, used widely in wind farms to obtain operational and condition information about wind turbines (WTs), is of important significance for anomaly detection in wind turbines. The paper presents a novel model for wind turbine anomaly detection mainly based on SCADA data and a back-propagation neural network (BPNN) for au...
متن کاملMonitoring Wind Turbine Vibration Based on SCADA Data
Three models for detecting abnormalities of wind turbine vibrations reflected in time domain are discussed. The models were derived from the supervisory control and data acquisition (SCADA) data collected at various wind turbines. The vibration of a wind turbine is characterized by two parameters, i.e., drivetrain and tower acceleration. An unsupervised data-mining algorithm, the k-means cluste...
متن کاملThe FuTure oF Wind Turbine diagnosTics
Wind energy is undergoing expansion, and it is bound to grow to a commercial/consumer level in the decades to come. This growth has materialized in the form of large-scale wind farms, wind energy cooperatives, wind turbines owned by individual investors, and multinational exploration of remote sites and offshore locations. Despite the increasing rated capacity of wind turbines, operation and ma...
متن کاملWAKE INDUCED POWER DEFICIT ANALYSIS ON WIND TURBINES IN FORESTEDMODERATELY COMPLEX TERRAIN USING SCADA DATA Dissertation in partial fulfillment of the requirements for the degree of MASTER OF SCIENCE WITH AMAJOR IN WIND POWER PROJECT MANAGEMENT
متن کامل
A New Method to Study Aggregation Effect of Harmonic Current Emissions in a Wind Farm Based on Type-III Wind Turbine Average Modeling
Assessment of complex harmonic current contribution of each wind turbines at connection point of a wind farm to the grid (primary emission) is presented in this paper. Moreover, contribution of grid background harmonic voltage distortion on harmonic current distortion (secondary emission) of each turbine is also evaluated. Both assessments are represented based on primary and secondary transfer...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2014