A Hybrid Model Based on Back-Propagation Neural Network and Optimized Support Vector Machine with Particle Swarm Algorithm for Assessing Blade Icing on Wind Turbines

With the continuous increase in the proportional use of wind energy across the globe,the reduction of power generation efficiency and safety hazards caused by the icing on wind turbine blades have attracted more consideration for research.Therefore,it is crucial to accurately analyze the thickness of icing on wind turbine blades,which can serve as a basis for formulating corresponding control measures and ensure a safe and stable operation of wind turbines in winter times and/or in high altitude areas.This paper fully utilized the advantages of the support vector machine(SVM)and back-propagation neural network(BPNN),with the incorporation of particle swarm optimization(PSO)algorithms to optimize the parameters of the SVM.The paper proposes a hybrid assessment model of PSO-SVM and BPNN based on dynamic weighting rules.Three sets of icing data under a rotating working state of the wind turbine were used as examples for model verification.Based on a comparative analysis with other models,the results showed that the proposed model has better accuracy and stability in analyzing the icing on wind turbine blades.

Research on the Icing Diagnosis ofWind Turbine Blades Based on FS–XGBoost–EWMA

In winter,wind turbines are susceptible to blade icing,which results in a series of energy losses and safe operation problems.Therefore,blade icing detection has become a top priority.Conventional methods primarily rely on sensor monitoring,which is expensive and has limited applications.Data-driven blade icing detection methods have become feasible with the development of artificial intelligence.However,the data-driven method is plagued by limited training samples and icing samples;therefore,this paper proposes an icing warning strategy based on the combination of feature selection(FS),eXtreme Gradient Boosting(XGBoost)algorithm,and exponentially weighted moving average(EWMA)analysis.In the training phase,FS is performed using correlation analysis to eliminate redundant features,and the XGBoost algorithm is applied to learn the hidden effective information in supervisory control and data acquisition analysis(SCADA)data to build a normal behavior model.In the online monitoring phase,an EWMA analysis is introduced to monitor the abnormal changes in features.A blade icing warning is issued when themonitored features continuously exceed the control limit,and the ambient temperature is below 0℃.This study uses data fromthree icing-affected wind turbines and one normally operating wind turbine for validation.The experimental results reveal that the strategy can promptly predict the icing trend among wind turbines and stably monitor the normally operating wind turbines.

Detecting Icing on the Blades of a Wind Turbine Using a Deep Neural Network

The blades of wind turbines located at high latitudes are often covered with ice in late autumn and winter,where this affects their capacity for power generation as well as their safety.Accurately identifying the icing of the blades of wind turbines in remote areas is thus important,and a general model is needed to this end.This paper proposes a universal model based on a Deep Neural Network(DNN)that uses data from the Supervisory Control and Data Acquisition(SCADA)system.Two datasets from SCADA are first preprocessed through undersampling,that is,they are labeled,normalized,and balanced.The features of icing of the blades of a turbine identified in previous studies are then used to extract training data from the training dataset.A middle feature is proposed to show how a given feature is correlated with icing on the blade.Performance indicators for the model,including a reward function,are also designed to assess its predictive accuracy.Finally,the most suitable model is used to predict the testing data,and values of the reward function and the predictive accuracy of the model are calculated.The proposed method can be used to relate continuously transferred features with a binary status of icing of the blades of the turbine by using variables of the middle feature.The results here show that an integrated indicator systemis superior to a single indicator of accuracy when evaluating the prediction model.

Influence of Surface Ice Roughness on the Aerodynamic Performance of Wind Turbines

The focus of this research was on the equivalent particle roughness height correction required to account for the presence of ice when determining the performances of wind turbines.In particular,two icing processes(frost ice and clear ice)were examined by combining the FENSAP-ICE and FLUENT analysis tools.The ice type on the blade surfaces was predicted by using a multi-time step method.Accordingly,the influence of variations in icing shape and ice surface roughness on the aerodynamic performance of blades during frost ice formation or clear ice formation was investigated.The results indicate that differences in blade surface roughness and heat flux lead to disparities in both ice formation rate and shape between frost ice and clear ice.Clear ice has a greater impact on aerodynamics compared to frost ice,while frost ice is significantly influenced by the roughness of its icy surface.