Parametric exploration on the airfoil design space by numerical design of experiment methodology and multiple regression model

Li, Xing-xing; Yang, Ke

doi:10.1177/0957650919850426

Cited by 3 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rıdvan et al [12] used orthogonal experimental analysis to study the effects of nozzle collection parameters and fluid composition parameters on the performance of electro-spray cooling, and they constructed a prediction model using the response surface methodology to optimize the electro-spray nozzle. Li et al [13] employed the optimal hypercube experimental design to examine the relationship between wind turbine airfoil design parameters and performance, and used multiple regression models to predict the impact of various design parameters on performance, analyzing the highly nonlinear relationships between design parameters and performance. Cheng et al [14] developed a mobile pump truck model and used finite element simulation to analyze the impact of design variables in the truck frame on overall pump truck performance, constructing a response surface prediction model based on simulation data to achieve the lightweight design of the pump truck frame.…”

Section: Introductionmentioning

confidence: 99%

Performance Prediction of the Elastic Support Structure of a Wind Turbine Based on Multi-Task Learning

Zhu,

Qi,

et al. 2024

Machines

View full text Add to dashboard Cite

The effectiveness of a wind turbine elastic support in reducing vibrations significantly impacts the unit’s lifespan. During the structural design process, it is necessary to consider the influence of structural design parameters on multiple performance indicators. While neural networks can fit the relationships between design parameters on multiple performance indicators, traditional modeling methods often isolate multiple tasks, hindering the learning on correlations between tasks and reducing efficiency. Moreover, acquiring training data through physical experiments is expensive and yields limited data, insufficient for effective model training. To address these challenges, this research introduces a data generation method using a digital twin model, simulating physical conditions to generate data at a lower cost. Building on this, a Multi-gate Mixture-of-Experts multi-task prediction model with Long Short-Term Memory (MMoE-LSTM) module is developed. LSTM enhances the model’s ability to extract nonlinear features from data, improving learning. Additionally, a dynamic weighting strategy, based on coefficient of variation weighting and ridge regression, is employed to automate loss weight adjustments and address imbalances in multi-task learning. The proposed model, validated on datasets created using the digital twin model, achieved over 95% predictive accuracy for multiple tasks, demonstrating that this method is effective.

show abstract

Section: Introductionmentioning

confidence: 99%

Performance Prediction of the Elastic Support Structure of a Wind Turbine Based on Multi-Task Learning

Zhu,

Qi,

et al. 2024

Machines

View full text Add to dashboard Cite

show abstract

“…Multiobjective optimization analysis was utilized by Govidan and Santiago 20 to investigate feasibility of power consumption reduction of NREL 5 MW wind turbine blade equipped with PA exploiting Qblade and MATLAB software. Li and Yang 21 obtained the airfoil design variables correlation with the airfoil aerodynamic, structural, and acoustic responses utilizing the regression model to decrease optimization computational cost.…”

Section: Introductionmentioning

confidence: 99%

Genetic algorithm optimization of a horizontal axis wind turbine blade section performance equipped with a single dielectric barrier discharge plasma actuator utilizing a direct regression model

Fadaei

Davari

Sabetghadam

2022

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

The usage of a single dielectric barrier discharge plasma actuator (SDBD-PA) device for improving a aerodynamic performance of a locally developed horizontal axis wind turbine blade section is studied with one of the most recent electrostatic models. To characterize this blade section behavior over a wide range of operating conditions of SDBD-PA and to advance its performance with a fully automated optimization algorithm, a computationally cost efficient direct regression model is proposed. In this paper, 512 comprehensive numerical simulations are carried out to derive the direct regression model for aerodynamic performance calculation when the PA is in use. However, to obtain highly accurate results, two different models for angle of attacks higher and less than [Formula: see text] are suggested. The proposed mathematical model within the specified boundary limits allows for a rapid linkage between aerodynamic performance and genetic algorithm which canbe made to acquire optimum results for each case without requiring burdensome numerical simulations. It is identified that superimpose input parameters effects onto each other is not explanatory of the final effect on aerodynamic performance and interaction effects should be seriously taken into consideration at the proposed regression model.

show abstract

Predicting pressure coefficients of wing surface based on the transfer of spatial dependency

Liu

et al. 2022

AIP Advances

View full text Add to dashboard Cite

Multi-conditional holographic pressure coefficients over a wing are crucial for wing design, and a wind tunnel test is an indispensable means to obtain this profile. However, it is resource-consuming to obtain wind tunnel data under different conditions and only a limited number of sensors can be placed on the wing model during one test, which results in sparse pressure coefficient data with distribution inconsistency across cross sections and conditions. Thus, how to obtain pressure coefficients of more cross sections or even the whole wing surface with multiple conditions from the distribution-inconsistent sensor data becomes a challenging problem. Therefore, a deep learning framework based on transfer learning is proposed in this paper, in which the spatial dependency captured by a long short-term memory model between the obtained multi-conditional sensor data is transferred to other cross sections with few-condition data on the wing. The results demonstrate that the proposed framework achieves high accuracy on the pressure coefficients prediction of distribution-inconsistent cross sections on wind tunnel test data, and thus improves data utilization and cuts costs by reducing wind tunnel tests under different design conditions. Our work proves the possibility of reconstructing the holographic flow field from sparse sensor data of wind tunnel tests and puts forward recommendations on the placement of sensors for achieving this goal.

show abstract

Parametric exploration on the airfoil design space by numerical design of experiment methodology and multiple regression model

Cited by 3 publications

References 33 publications

Performance Prediction of the Elastic Support Structure of a Wind Turbine Based on Multi-Task Learning

Performance Prediction of the Elastic Support Structure of a Wind Turbine Based on Multi-Task Learning

Genetic algorithm optimization of a horizontal axis wind turbine blade section performance equipped with a single dielectric barrier discharge plasma actuator utilizing a direct regression model

Predicting pressure coefficients of wing surface based on the transfer of spatial dependency

Contact Info

Product

Resources

About