An explainable AI framework for robust and transparent data-driven wind turbine power curve models

In recent years,increasingly complex machine learning methods have become state-of-the-art in modelling wind turbine power curves based on operational data.While these methods often exhibit superior performance on test sets,they face criticism due to a perceived lack of transparency and concerns about their robustness in dynamic,non-stationary environments encountered by wind turbines.In this work,we address these issues and present a framework that leverages explainable artificial intelligence methods to gain systematic insights into data-driven power curve models.At its core,we propose a metric to quantify how well a learned model strategy aligns with the underlying physical principles of the problem.This novel tool enables model validation beyond the conventional error metrics in an automated manner.We demonstrate,for instance,its capacity as an indicator for model generalization even when limited data is available.Moreover,it facilitates understanding how decisions made during the machine learning development process,such as data selection,pre-processing,or training parameters,affect learned strategies.As a result,we obtain physically more reasonable models,a prerequisite not only for robustness but also for meaningful insights into turbine operation by domain experts.The latter,we illustrate in the context of wind turbine performance monitoring.In summary,the framework aims to guide researchers and practitioners alike toward a more informed selection and utilization of data-driven wind turbine power curve models.

A method for cleaning wind power anomaly data by combining image processing with community detection algorithms

Current methodologies for cleaning wind power anomaly data exhibit limited capabilities in identifying abnormal data within extensive datasets and struggle to accommodate the considerable variability and intricacy of wind farm data.Consequently,a method for cleaning wind power anomaly data by combining image processing with community detection algorithms(CWPAD-IPCDA)is proposed.To precisely identify and initially clean anomalous data,wind power curve(WPC)images are converted into graph structures,which employ the Louvain community recognition algorithm and graph-theoretic methods for community detection and segmentation.Furthermore,the mathematical morphology operation(MMO)determines the main part of the initially cleaned wind power curve images and maps them back to the normal wind power points to complete the final cleaning.The CWPAD-IPCDA method was applied to clean datasets from 25 wind turbines(WTs)in two wind farms in northwest China to validate its feasibility.A comparison was conducted using density-based spatial clustering of applications with noise(DBSCAN)algorithm,an improved isolation forest algorithm,and an image-based(IB)algorithm.The experimental results demonstrate that the CWPAD-IPCDA method surpasses the other three algorithms,achieving an approximately 7.23%higher average data cleaning rate.The mean value of the sum of the squared errors(SSE)of the dataset after cleaning is approximately 6.887 lower than that of the other algorithms.Moreover,the mean of overall accuracy,as measured by the F1-score,exceeds that of the other methods by approximately 10.49%;this indicates that the CWPAD-IPCDA method is more conducive to improving the accuracy and reliability of wind power curve modeling and wind farm power forecasting.

On Advanced Control Methods toward Power Capture and Load Mitigation in Wind Turbines

This article provides a survey of recently emerged methods for wind turbine control. Multivariate control approaches to the optimization of power capture and the reduction of loads in components under time-varying turbulent wind fields have been under extensive investigation in recent years. We divide the related research activities into three categories： modeling and dynamics of wind turbines, active control of wind turbines, and passive control of wind turbines. Regarding turbine dynamics, we discuss the physical fundamentals and present the aeroelastic analysis tools. Regarding active control, we review pitch control, torque control, and yaw control strategies encompassing mathematical formulations as well as their applications toward different objectives. Our survey mostly focuses on blade pitch control, which is considered one of the key elements in facilitating load reduction while maintaining power capture performance. Regarding passive control, we review techniques such as tuned mass dampers, smart rotors, and microtabs. Possible future directions are suggested.

Effect of blade pitch angle on aerodynamic performance of straight-bladed vertical axis wind turbine

Wind energy is one of the most promising renewable energy sources, straight-bladed vertical axis wind turbine(S-VAWT) appears to be particularly promising for the shortage of fossil fuel reserves owing to its distinct advantages, but suffers from poor self-starting and low power coefficient. Variable-pitch method was recognized as an attractive solution to performance improvement, thus majority efforts had been devoted into blade pitch angle effect on aerodynamic performance. Taken into account the local flow field of S-VAWT, mathematical model was built to analyze the relationship between power outputs and pitch angle. Numerical simulations on static and dynamic performances of blade were carried out and optimized pitch angle along the rotor were presented. Comparative analyses of fixed pitch and variable-pitch S-VAWT were conducted, and a considerable improvement of the performance was obtained by the optimized blade pitch angle, in particular, a relative increase of the power coefficient by more than 19.3%. It is further demonstrated that the self-starting is greatly improved with the optimized blade pitch angle.