New analytical wake models based on artificial intelligence and rivalling the benchmark full-rotor CFD predictions under both uniform and ABL inflows

Kabir, Ijaz Fazil Syed Ahmed; Safiyullah, Ferozkhan; Ng, E. Y. K.; Tam, Vivian W.Y.

doi:10.1016/j.energy.2019.116761

Cited by 21 publications

(8 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the CFWT, which is a small-scale turbine, can be used in buildings instead of VAWTs. Artificial Intelligence (AI) approaches can be used for the identification and assessment of wind power, WT locations, and their performance in urban environments by using the validated CFD literature in various urban configurations [196][197][198][199]. Recently, these approaches have become popular due to their high precision, strong adaptability, and improved learning capability.…”

Section: Applications In Urban Buildingsmentioning

confidence: 99%

A Comprehensive Review on Development and Applications of Cross-Flow Wind Turbines

2023

View full text Add to dashboard Cite

The rapid globalization of the energy crisis and the adverse effects of global warming have caused the need for non-conventional energy resources to be felt more than ever. As a result of this, vertical axis wind turbines (VAWT) have received much attention over the recent decades, and have thus been more developed and used worldwide. The cross-flow wind turbine (CFWT) is a wind turbine in the category of VAWTs, and perfectly suitable for urban applications due to its simplicity, high starting torque at low wind speed, and self-starting capability, even though its low power coefficient as its main drawback has slowed down its widespread use so far. The main aim of this paper is to review the scientific literature and recent developments in the field of CFWTs. The governing equations and turbulence models for the simulation of the turbine are discussed and various wind resource assessment methods for estimating potential site locations, different aspects, and wind energy harvesting systems from buildings are debated. The research gaps, challenges, and future possible works on such turbines and their applications are discussed. Investigations indicate that changing the rotor geometric parameters and adding innovative augmentation devices have been the most widely addressed approaches for making performance enhancement of the wind turbine in the literature. The critical performance-affecting parameters are improved by various innovative designs of the turbine structure or blades, as well as several augmentation techniques, such as guide nozzle, casing, windshield, guide vane, deflector, cowling, etc.

show abstract

Section: Applications In Urban Buildingsmentioning

confidence: 99%

A Comprehensive Review on Development and Applications of Cross-Flow Wind Turbines

2023

View full text Add to dashboard Cite

show abstract

“…Since the wake is fully developed in this far‐wake region and, in the hypothetical absence of ambient shear flow, the perturbation profiles of velocity deficit and turbulence intensity are assumed to be axisymmetric and have self‐similar distributions in the wake cross‐sections. These self‐similar and axisymmetric properties then become the basis of analytical models to predict the wake velocity profiles using either top‐hat shape 5–7 or Gaussian shape distribution 8–21 …”

Section: Introductionmentioning

confidence: 99%

“…These selfsimilar and axisymmetric properties then become the basis of analytical models to predict the wake velocity profiles using either top-hat shape [5][6][7] or Gaussian shape distribution. [8][9][10][11][12][13][14][15][16][17][18][19][20][21] One of the pioneering works in analytical wake modeling is the top-hat shape wake model proposed by Jensen in his technical report 5 and polished by Katić et al 6 This model was derived by only considering the mass conservation equation. The wake velocity was described in a much-idealized way where the velocity inside the wake region was considered constant.…”

Section: Introductionmentioning

confidence: 99%

“…Given the paramount of this wake velocity prediction, many investigations have been conducted to model detailed velocity field within the wake region 5–36 . Generally, the wake velocity field can be modeled with simple analytical models 5–21 or more sophisticated numerical approaches based on computational fluid dynamics (CFD) 22–37 . Despite being less accurate than CFD‐based approaches, the simplicity of analytical models and their low computational cost make the analytical approach the preferred choice for optimizing the wind farm layout 3,38 .…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Anisotropic double‐Gaussian analytical wake model for an isolated horizontal‐axis wind turbine

Soesanto

Yoshinaga

Iida

2022

Energy Science & Engineering

View full text Add to dashboard Cite

An anisotropic double Gaussian (DG) model for analytical wake modeling to predict the streamwise wake velocity behind an isolated non-yawed horizontal-axis wind turbine is proposed. The proposed model is based upon the conservation of mass and momentum inside a streamtube control volume. The wake growth rate parameters to distinguish the wake expansion rate between lateral and vertical directions were tuned based on numerical and measurement data of utility-scale turbines. It was found that the proposed model can give feasible predictions within the full-wake region under different inflow conditions. In addition, the other analytical models based on top-hat shape and single Gaussian approaches were evaluated for comparison. The root-mean-square error statistical analysis was used to evaluate the performance of each examined model under different flow conditions. In general, the proposed model outperformed the other examined models in all wake region categories, particularly within the near-wake region and the onset of the far-wake region, which are beyond the scope of the conventional approach for analytical wake modeling. This advantage gives the potential for the proposed model to provide a better prediction for the wake flow estimation within tightly packed wind farms.

show abstract

On the Limitations of Machine Learning (ML) Methodologies in Predicting the Wake Characteristics of Wind Turbines

Gajendran

Kabir

Purohit

et al. 2022

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Machine Learning (ML) algorithms have been more prevalent in recent years, and they are being used to tackle complicated issues across a broad range of fields. Wind energy is not an exception, as ML has recently been applied to wind turbine blade design, wake velocity and wake turbulence intensity prediction, and even wind farm optimization. The immense learning ability of ML models enables them to be trained to predict and regress a complex relationship with a high degree of accuracy. However, data for testing ML models often originate from the same rotor simulation used for training, with just slight variations in operating conditions. This research aims to investigate the generalizability of ML-based wake prediction models, i.e., whether ML can correctly predict wake properties using data from a different wind turbine that was not taken for training. This investigation's observation shows that a generalized ML wake model requires training data from multiple turbines with a wide range of operating conditions. In addition, advanced regularization, complex loss functions, and ML methods that focus on capturing the physics (such as Physics Informed Artificial Neural Networks (PINN) and symbolic regression) can be utilized.

show abstract

New analytical wake models based on artificial intelligence and rivalling the benchmark full-rotor CFD predictions under both uniform and ABL inflows

Cited by 21 publications

References 35 publications

A Comprehensive Review on Development and Applications of Cross-Flow Wind Turbines

A Comprehensive Review on Development and Applications of Cross-Flow Wind Turbines

Anisotropic double‐Gaussian analytical wake model for an isolated horizontal‐axis wind turbine

On the Limitations of Machine Learning (ML) Methodologies in Predicting the Wake Characteristics of Wind Turbines

Contact Info

Product

Resources

About