Wind Turbine Research Articles

Application of Artificial Intelligence in Wind Power New Energy Grid Integration Planning and Scheduling

Wind power integration into existing energy grids presents significant challenges in managing variable energy generation, grid stability, and scheduling optimization. Factors such as fluctuating wind power output, conventional grid generation, battery storage capacity, and varying load demands influence system performance in achieving effective energy distribution and integration. A novel bio-inspired resilient manta ray foraging (Res-MRF) optimization algorithm is applied to address these challenges in the actual-time planning and scheduling of power generation, storage, and load management in a wind-powered new energy grid. Initially, data were collected that comprise power generated by wind turbines. Then preprocessing using Z-score normalization is performed to standardize data effectively. Further, a maximum power point tracking algorithm based on the wind speed values from the dataset is implemented to predict the maximum power output. The suggested method is implemented using Python software. Finally, the proposed Res-MRF-based approach intelligently allocates resources, balances grid load, and reduces operational costs while ensuring sustainable energy delivery and user demand satisfaction. Extensive simulations validate the efficacy of the Res-MRF technique, demonstrating efficient reduction in total energy costs and improved grid efficiency, while ensuring that renewable energy resources are effectively utilized. These results highlight the potential of artificial intelligence-driven optimization in enhancing the integration of wind power into new energy grids.

Numerical investigation of transition on a wind turbine blade under free stream turbulence at $\boldsymbol {Re_c=10^6}$

Laminar–turbulent transition on the suction surface of the LM45.3p blade ( $20\,\%$ thickness) was investigated using wall-resolved large eddy simulation (LES) at a chord Reynolds number of $Re_c=10^6$ and angle of attack $4.6^\circ$ . The effects of anisotropic free stream turbulence (FST) with intensities $TI=0\,\%$ – $7\,\%$ were examined, with integral length scales scaled down from atmospheric measurements. At $TI=0\,\%$ , a laminar separation bubble (LSB) forms and transition is initiated by Kelvin–Helmholtz vortices. At low FST levels ( $0\,\%\lt TI \leqslant 2.4\,\%$ ), robust streak growth via the lift-up mechanism suppresses the LSB, while transition dynamics shifts from two-dimensional Tollmien–Schlichting (TS) waves ( $TI=0.6\,\%$ ) to predominantly varicose inner and outer instabilities ( $TI=1.2\,\%$ and $2.4\,\%$ ) induced by the wall-normal shear and inflectional velocity profiles. The critical disturbance kinetic energy scales with $TI^{-1.80\pm 0.11}$ , compared with $TI^{-2.40}$ from Mack’s correlation. For $TI\geqslant 4.5\,\%$ , bypass transition dominates, driven by high-frequency boundary layer perturbations and streak breakdown via outer sinuous modes induced by the spanwise shear and inflectional velocity profiles. The scaling of streak amplitudes with $TI$ becomes sub-linear and spanwise non-uniformity characterises the turbulent breakdown. The critical disturbance kinetic energy reduces to $TI^{-0.90\pm 0.16}$ , marking a transition regime distinct from modal mechanisms. The onset of bypass transition ( $TI\approx 2.4\,\%{-}4.5\,\%$ ) aligns with prior studies of separated and flat-plate flows. A proposed turbulence spectrum cutoff links atmospheric measurements to wind tunnel data and Mack’s correlation, offering a framework for effective $TI$ estimation in practical environments.

Deep Learning-Based Fault Diagnosis via Multisensor-Aware Data for Incipient Inter-Turn Short Circuits (ITSC) in Wind Turbine Generators

Wind energy is a vital pillar of modern sustainable power generation, yet wind turbine generators remain vulnerable to incipient inter-turn short-circuit (ITSC) faults in their stator windings. These faults can cause fluctuations in the output voltage, frequency, and power of wind turbines, eventually leading to overheating, equipment damage, and rising maintenance costs if not detected early. Although significant progress has been made in condition monitoring, the current methods still fall short of the robustness required for early fault diagnosis in complex operational settings. To address this gap, this study presents a novel deep learning framework that involves traditional baseline machine-learning algorithms and advanced deep network architectures to diagnose seven distinct ITSC fault types using signals from current, vibration, and axial magnetic flux sensors. Our approach is rigorously evaluated using metrics such as confusion matrices, accuracy, recall, average precision (AP), mean average precision (mAP), hypothesis testing, and feature visualization. The experimental results demonstrate that deep learning models outperform machine learning algorithms in terms of precision and stability, achieving an mAP of 99.25% in fault identification, with three-phase current signals emerging as the most reliable indicator of generator faults compared to vibration and electromagnetic data. It is recommended to combine three-phase current sensors with deep learning frameworks for the precise identification of various types of incipient ITSC faults. This study offers a robust and efficient pipeline for condition monitoring and ITSC fault diagnosis, enabling the intelligent operation of wind turbines and maintenance of their operating states. Ultimately, it contributes to providing a practical way forward in enhancing turbine reliability and lifespan.

Fatigue assessment of offshore tubular joints: stress concentration factor vs. detailed finite element method using stress influence matrix

ABSTRACT In this work, two hotspot stress estimation methods were compared in prediction of the fatigue damage level of tubular joints of jacket-supported offshore wind turbines (OWT). The first method is the stress concentration factor (SCF) method, which uses empirical functions to determine eight hotspot stresses (HSSs) along the brace-chord weld interface of each tubular joint. The second method is the stress influence matrix (SIM) method, which is based on a single realization of detailed finite element simulation of tubular joints, determining HSSs through matrix multiplication and linear stress extrapolation. After determined HSSs, fatigue damage is computed using the rainflow counting and S-N curve. Two complete fatigue damage analysis processes for the tubular joints (TJs) of OWT were proposed. Furthermore, an implementation study involving TJ1-TJ5 of the reference NREL 5 MW OWT was presented. The results through comparison indicate that the SIM-incorporated fatigue assessment procedure that considers an extended number of hotspots on the inner or outer wall of the joint member could lead to a more precise fatigue analysis. The SIM-incorporated fatigue assessment procedure provides an optimal and less conservative solution for FLS design in view of the fact that the discrepancy between the SCF- and SIM-incorporated fatigue procedures increases with the joint elevation level.

Failure Mode and Effect Analysis of Complex Electromechanical Systems Based on Personalized Consensus in Heterogeneous Environment

ABSTRACTFailure mode effect analysis (FMEA) is a powerful reliability analysis tool for identifying and eliminating potential risks in complex electromechanical systems (CESs). However, due to the uncertainty of the decision‐making environment, processing heterogeneous risk information becomes a challenge. In addition, the consensus of the evaluation subjects (ESs) and the interaction of failure modes (FMs) is often easily overlooked. To address these challenges, we propose an improved FMEA method in heterogeneous environment based on personalized consensus. First, a heterogeneous house of reliability (H‐HoR) is proposed to identify multi‐source heterogeneous information. Second, a consensus model based on D‐S evidence theory is proposed to adjust the opinions of different acceptability individually. Meanwhile, an adaptive ES weight determination method based on individual characteristics and maximum consensus is proposed. Then, to avoid information loss, an improved hybrid method of ELimination Et Choix Traduisant la REalité (ELECTRE) with Vlsekriterijumska Optimizacija I Kompromisno Resenje (VIKOR) is proposed to rank FMs in heterogeneous environments. Furthermore, based on the extended K‐shell method, the interaction of FMEA in aspects of strength and community relationships is considered to obtain more accurate ranking results. Finally, the effectiveness and practicality can be verified from the case of an offshore wind turbine transmission system. This research has excellent accuracy and superiority and is expected to support integrated research on system reliability.

Enhanced forecasting of bird nocturnal migration intensity in relation to previous days and synoptic weather patterns.

Operational bird migration forecast models have recently offered promising perspectives for mitigating the impacts of human activities on avifauna. These models improve on simple phenological expectations by harnessing the intricate relationship between bird movements and weather conditions to forecast migration fluxes days in advance. However, state-of-the-art models face limitations as bird fluxes are often simply modelled as a response to local and instantaneous weather without accounting for previous and synoptic weather patterns. This study focuses on enhancing bird migration forecasts by evaluating the contributions of weather dynamics at various spatial and temporal scales. We use bird vertical density data from 9 French weather radars over 6 years and employ gradient-boosted regression trees for predictions. Dimension reduction tools are used to describe local and continental-scale weather conditions from the previous three days. We also explore the contributions of the different meteorological metrics considered using explainable regression trees tools. Our model improved phenology models by explaining about 1.3 and 2.25 times more additional variance than approaches based on local and instantaneous weather conditions in spring and autumn, respectively. Local and instantaneous weather metrics contributed the most, but they mainly helped identifying nights with low migration. In contrast, weather metrics for previous 3 days were crucial to forecast highest intensity migration events, as they enabled to account for bird accumulation in relation to unfavorable weather locally and remotely. This study enhanced forecast accuracy and contributed to a deeper understanding of the factors influencing bird migration. It enabled the identification local and synoptic weather patterns related to important migration events without a priori knowledge. It is therefore easy to interpret, easy to transfer to other ecological systems, and promising for the accurate forecast of migration peaks. Forecasted peaks can guide conservation efforts, for example by dimming lights for birds at night or by shutting down wind turbines.

Characteristics Improvement of Brushless Doubly-Fed Wind Turbine Generator with Minimized Asymmetric Phenomena

Compared with the traditional brushless doubly-fed generator (BDFG), the BDFG with double stator (BDFG-DS) architecture achieves enhanced configurability by physically decoupling the power and control windings onto independent stator assemblies. The design offers benefits such as expanded slot dimensions and enhanced power density, yet it remains constrained by inherent asymmetry in three phases, which causes large harmonics and torque ripples. In this paper, the working mechanism of the BDFG-DS is introduced. Then the root cause of the asymmetric phenomena is discussed. And based on the analysis, an optimization method with complementary skewed stators is developed to enhance the performance of the BDFG-DS. By adopting the appropriate combination of pole slot and skewing slot angles of the two stators, the asymmetry and performance, including harmonics and torque ripples, are improved. Meanwhile, unlike the traditional skewing slot method, the torque density and power density are not decreased. Finally, a finite element analysis model is built and simulations are conducted to demonstrate the electromagnetic optimization efficacy of the proposed skewed-stator topology.

TLP-Supported NREL 5MW Floating Offshore Wind Turbine Tower Vibration Reduction Under Aligned and Misaligned Wind-Wave Excitations

This paper presents a numerical study on the structural vibrations of a TLP-supported NREL 5MW wind turbine equipped with a tuned vibration absorber (TVA) in the nacelle. The analysis was focused on tower bending deflections and was conducted using a reference OpenFAST V3.5.3 dedicated wind turbine modelling software and a finite element simulation framework based on Comsol Multiphysics V6.3 which was newly developed for this study. The obtained four-degree-of-freedom (4-DOF) tower bending model was transferred using modal decomposition to the MATLAB/Simulink R2020b environment, where a 2-DOF TLP surge/sway model and a bidirectional (2-DOF) TVA model were embedded. The wind field was approximated by a Weibull distribution of velocities (8.86 m/s mean, 4.63 m/s standard deviation). It was combined with the wave actions simulated using a Bretschneider spectrum with a significant height of 2.5 m and a peak period of 8.1 s. The TVA model used was either the standard NREL reference 20-ton passive TVA, a 10-ton passive, or a 10-ton controlled TVA (the latter two tuned to the tower’s first bending mode). The controlled TVA utilised a magnetorheological (MR) damper, either operating independently (forming a semi-active MR-TVA) or simultaneously with a force actuator, forming, in this case, a hybrid H-MR-TVA. Both aligned and 45°/90° misaligned wind–wave excitations were examined to investigate the performance of a 10-ton real-time controlled (H-)MR-TVA operating with less working space. In aligned conditions, the semi-active and hybrid MR-TVA solutions demonstrated superior tower vibration mitigation, reducing maximum tower deflections by 11.2% compared to the reference TVA and by 14.9% with regard to the structure without TVA. The reduction in root-mean-square deflection reached up to 4.2%/2.9%, respectively, for the critical along-the-waves direction, while the TVA stroke reduction reached 18.6%. For misaligned excitations, the tower deflection was reduced by 4.3%/4.8% concerning the reference 20-ton TVA, while the stroke was reduced by 22.2%/34.4% (for 45°/90° misalignment, respectively). It is concluded that the implementation of the 10-ton real-time controlled (H-)MR-TVA is a promising alternative to the reference 20-ton passive TVA regarding tower deflection minimisation and TVA stroke reduction for the critical along-the-waves direction. The current research results may be used to design a full-scale semi-active or hybrid TVA system serving a TLP-supported floating offshore wind turbine structure.

Quantum Computing as a Catalyst for Microgrid Management: Enhancing Decentralized Energy Systems Through Innovative Computational Techniques

This paper introduces a groundbreaking framework for optimizing microgrid operations using the Quantum Approximate Optimization Algorithm (QAOA). The increasing integration of decentralized energy systems, characterized by their reliance on renewable energy sources, presents unique challenges, including the stochastic nature of energy supply-and-demand management. Our study leverages quantum computing to enhance the operational efficiency and resilience of microgrids, transcending the limitations of traditional computational methods. The proposed QAOA-based model formulates the microgrid scheduling problem as a Quadratic Unconstrained Binary Optimization (QUBO) problem, suitable for quantum computation. This approach not only accommodates complex operational constraints—such as energy conservation, peak load management, and cost efficiency—but also dynamically adapts to the variability inherent in renewable energy sources. By encoding these constraints into a quantum-friendly Hamiltonian, QAOA facilitates a parallel exploration of multiple potential solutions, enhancing the probability of reaching an optimal solution within a feasible time frame. We validate our model through a comprehensive simulation using real-world data from a microgrid equipped with photovoltaic systems, wind turbines, and energy storage units. The results demonstrate that QAOA outperforms conventional optimization techniques in terms of cost reduction, energy efficiency, and system reliability. Furthermore, our study explores the scalability of quantum algorithms in energy systems, providing insights into their potential to handle larger, more complex grid architectures as quantum technology advances. This research not only underscores the viability of quantum algorithms in real-world applications but also sets a precedent for future studies on the integration of quantum computing into energy management systems, paving the way for more sustainable, efficient, and resilient energy infrastructures.

Enhancing the backstepping control approach competencies for wind turbine systems using a dual star induction generator

The goal of this study is to present a novel and improved backstepping control (BC) technique for a dual-star induction generator (DSIG) powered by a wind turbine. This approach relies on the ant lion optimization (ALO), which is employed to determine the optimal parameters of the BC approach and improve the performance of the wind conversion energy system. The ALO approach enhances the robustness of the DSIG, enabling faster dynamic responses, greater accuracy, and consistently improved effectiveness. The fitness function of the ALO approach integrates both integral time absolute error and integral time squared error criteria, ensuring the fulfillment of effectiveness objectives. The performance of the BC-ALO approach is validated through MATLAB. The results of the tests show that the new approach reduces total harmonic distortion, minimizes stator energy fluctuations, and improves dynamic efficiency compared to the BC approach. Additionally, the method can handle uncertainties in model parameters, making it versatile and practical. Simulation results show that the BC-ALO method reduces the total harmonic distortion value compared to the BC method by percentages estimated at 29.45%, 50.44%, and 43.10% in all tests. Also, this approach improves the overshoot value of DSIG power compared to the traditional BC strategy by an estimated 100% in all tests. The proposed approach improves the response time value of the reactive power compared to the conventional BC strategy by percentages estimated at 97.65%, 97.78%, and 95.23% in all tests. The DC link voltage ripples are low if the proposed approach is used, with ratios estimated at 63.31%, 71.38%, and 71.89% in all tests. These results make the proposed approach interesting in other applications such as photovoltaic systems.

Design of a novel noise resilient algorithm for fault detection in wind turbines on supervisory control and data acquisition system

Wind turbine faults, including electrical, mechanical or aerodynamics-related, can potentially reduce operational efficiency, causing downtimes or, in some cases, leading to severe damage. Hence, timely detection of these operational anomalies is crucial for optimizing performance and reducing maintenance costs. The following study explores the application of Supervisory Control and Data Acquisition (SCADA) data for fault detection and diagnosing different operational states in wind turbines by focusing on environmental and operational factors which affect the performance. An efficient noise-resilient classification framework is proposed which includes a novel Perturbed-Random Forest (P-RF) algorithm to diagnose operational states with high accuracy even under noisy conditions. Seasonal discrepancies in power generation are analyzed using theoretical and actual power analysis. Further, distributions of features are realized via kernel density estimation and efficiency metrics in order to identify performance inefficiencies. The P-RF algorithm achieved 99.72% accuracy in diagnosing the status of the SCADA-based wind turbine although with a slightly higher computational complexity than a baseline Random Forest algorithm. Multiple Evaluation metrics were employed to assess the performance of the proposed model under different signal-to-noise conditions.

Retrofitting Methods for Existing Wind Turbine Foundations and Their Responses Under Wind Loads

Retrofitting Methods for Existing Wind Turbine Foundations and Their Responses Under Wind Loads

Towing Resistance and Design of a Towing Scheme for a Floating Wind Turbine

Towing operation is an important part of the transportation and installation of offshore floating wind turbines. The study of towing resistance is of great significance to the efficient construction of floating wind turbine towing. This paper takes the floating wind turbine model designed by “China Energy Construction Group Guangdong Electric Power Design Institute Co., Ltd.” as the research object, uses STAR-CCM+ 2302 software to establish the computational domain model of floating wind turbine towing, and compares it with the existing physical model experimental results and empirical formula calculation results to verify the accuracy of the CFD resistance prediction method; then the method is used to calculate the still water towing resistance of the new large-megawatt floating wind turbine at different drafts and speeds, and according to the resistance calculation results, the integrated towing system of the floating wind turbine is established in ANSYS-AQWA (Version 2023 R1), the influence of environmental loads on towing resistance is analyzed, and the selection basis of tugboat is proposed. The results show that towing resistance is closely related to the draft, speed, and foundation configuration of the wind turbine platform. In order to ensure the safety of the towing system, the speed should be kept below 4 kn. The experimental results are compared and verified that the calculation results of this method are close to the experimental values and the empirical formula calculation values, which realizes the rapid prediction of the towing resistance of the floating wind turbine and provides guidance for the towing operation of the offshore floating wind turbine platform.

Aerodynamic and aeroelastic analyses of a split-winglet blade for horizontal axis wind turbine

Aerodynamic and aeroelastic analyses of a split-winglet blade for horizontal axis wind turbine

Novel design of rotary pontoon floating wind turbine reliability assessment by self-deconvolution method

As the offshore wind energy industrial sector develops dynamically towards its economic viability targets, it is important to continuously improve structural design, while increasing energy output and minimizing operational repair downtime. Large horizontal-axis wind turbines (HAWTs) are already commonplace and they are in the process of being designed on a larger scale, which is challenging. Vertical-axis wind turbines (VAWTs), where the tilt of the axis of rotation is not a concern, constitute an alternative to HAWTs in the field of for floating offshore wind turbines design. This case study presents hydrodynamic loads analysis and structural failure risk assessment for the novel offshore cross-flow vertical axis Wind Energy Marine Unit (WEMU) with a large floating rotor design. The primary goal of this research was to assess the structural operational reliability of the novel WEMU design, given realistic environmental conditions. Environmental wave loads acting on the torus of the semi-submersible pontoon during its rotation had been modeled numerically. Subsequently, structural risk failure was assessed, utilizing a state-of-the-art self-deconvolution extrapolation scheme. Reliability prognostic results had been cross-validated versus the existing four-parameter Weibull fit method. To summarize, the presented case study combines a novel structural design with a recently developed reliability method. The latter can be of practical engineering use for contemporary floating wind turbine design.

A machine-learning optimized vertical-axis wind turbine

Abstract Vertical-axis wind turbines (VAWTs) have garnered increasing attention in the field of renewable energy due to their unique advantages over traditional horizontal-axis wind turbines (HAWTs). However, traditional VAWTs including Darrieus and Savonius types suffer from significant drawbacks -- negative torque regions exist during rotation. In this work, we propose a new design of VAWT, which combines design principles from both Darrieus and Savonius but addresses their inherent defects. The performance of the proposed VAWT is evaluated through numerical simulations and validated by experimental testing. The results demonstrate that its power output is approximately three times greater than that of traditional Savonius VAWTs of comparable size. The performance of the proposed VAWT is further optimized using machine learning techniques, including Gaussian process regression and neural networks, based on extensive supercomputer simulations. This optimization leads to a 30% increase in power output.

Optimizing the sizing of residential microgrids using a genetic algorithm as a decision support model

PurposeThis study evaluates the performance of genetic algorithms (GAs) in optimizing the sizing of wind photovoltaic systems with battery energy storage systems (BESS). The objective is to determine whether GAs can balance generation and storage, improve system autonomy, reduce operating costs and meet residential energy demand in real-world environments.Design/methodology/approachA genetic algorithm was used as a multi-objective optimization tool to determine the optimal sizing of solar panels, wind turbines and BESS. The model considers energy demand, climate variability and resource intermittency. Metrics such as autonomy, total costs and total energy deficit (TED) were evaluated. The results were compared with the exhaustive search to validate the effectiveness of the GA.FindingsThe GA identified an optimal configuration with a TED of 3.76%, an autonomy of 96.24% and an efficiency of 95% and a total cost of USD 7,500. In contrast, the exhaustive search achieved a TED of 4.3%, a range of 95.7% and an efficiency of 90% at a cost of USD 8,000. Although both methods ensure optimal performance, GA stands out for its computational efficiency and ability to balance multiple targets.Originality/valueThis study not only highlights the usefulness of GAs for designing hybrid microgrids that address renewable resource intermittency and economic viability but also contributes to the sustainable development goal by promoting sustainable and affordable solutions for residential communities.

Spatial development of planar and axisymmetric wakes of porous objects under a pressure gradient: a wind tunnel study

Abstract. We report an experimental study on the effect of a constant adverse pressure gradient on the spatial evolution of turbulent wakes generated by different objects. A porous disc, designed to mimic the wake of a horizontal-axis wind turbine, and a porous cylinder, whose wake matches that of a vertical-axis wind turbine, were tested in a wind tunnel for Reynolds numbers (based on the generator diameter) in the range of 2.6×105 to 3.9×105. Experiments were conducted between 1 and 7 diameters downstream of the disc and from 2 to 12 diameters downstream of the cylinder. We find that the effect of the adverse pressure gradient is significant in all cases, resulting in larger velocity deficits and wider wakes. Moreover, these variations are stronger for the cylinder-generated wake. We also find that current analytical models for wakes evolving in pressure gradients, developed from momentum conservation, satisfactorily fit our data. Our results provide a benchmark case that will contribute to improving energy harvesting in cases where pressure gradients are relevant, such as in wind plants installed over complex topographies and tidal stream generators.

A Symmetry-Aware Pitch Feature Encoder–Decoder Network for Condition Monitoring of Pitch Bearings in Wind Turbines

A Symmetry-Aware Pitch Feature Encoder–Decoder Network for Condition Monitoring of Pitch Bearings in Wind Turbines

Rolling Contact Fatigue Behavior of Pitch Bearing Raceway in Offshore Wind Turbines

As critical components in offshore wind turbine (OWT) systems, pitch bearings require exceptional fatigue resistance to ensure the extended operational lifespan and structural reliability demanded by marine environments. Failure of these bearings due to rolling contact fatigue (RCF) can severely affect the economic efficiency of offshore wind turbines and potentially lead to safety accidents involving both humans and machinery. A simulation model for pitch bearings used in a 3 MW OWT is established to study the RCF behavior under operational conditions based on continuum damage mechanics. Both the elastic and plastic damage are considered in the damage process through a Python script. A user subroutine UMAT is programmed to depict the gradual deterioration of mechanical properties. The results indicate that the fatigue damage of the raceway exhibits significant nonlinear characteristics, with elastic damage playing a predominant role in determining its fatigue life under operational conditions.