Optimization of Blowing Jet Performance on Wind Turbine Airfoil Under Dynamic Stall Conditions Using Active Machine Learning and Computational Intelligence

Kasmaiee, Si.; Tadjfar, Mehran; Kasmaiee, Sa.

doi:10.1007/s13369-023-07892-9

Cited by 16 publications

(5 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this step, the hyper-parameters used to train a DL model are optimized using GA, as shown in Algorithm 1. Based on the algorithm, some parameters need to be defined, i.e., Lines 2-6, where the parameters are defined as follows, population_size = 75 num_generations = 3 mutation_rate = 0.2 parameter_choices = {'nb_neurons': [10,20,30,40,50,60,70,80],…”

Section: Results Of Hyper-parameter Optimization (Step 4)mentioning

confidence: 99%

“…Deep learning (DL) is a powerful ML technique that utilizes computational models of neural network inspired by the structure of the human brain [10], [11] for modeling complex and non-linear design parameters. However, the effectiveness of DL often comes at the cost of demanding significant computational resources due to the complex architecture of the networks.…”

Section: Introductionmentioning

confidence: 99%

“…The GA is a robust meta-heuristic algorithm inspired by natural selection, where the algorithm can efficiently explore high-dimensional and non-convex search spaces, capable of handling complex relationships between hyper-parameters and network performance [10], [14]. GA creates a population of candidate solutions, subjecting them to selection, crossover, and mutation to converge towards the optimal solution.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep learning-based prediction of float model performance in floatplanes: A case study on lift-to-drag coefficient ratio

Fahmi,

Fajar,

Atmaja

et al. 2024

IJ-AI

View full text Add to dashboard Cite

Developing an engineering design is resource-intensive and time-consuming, particularly for the floats of a floatplane design, due to its complexity and limited testing facilities. Intelligent-based computational design (IBCD) techniques, which integrate computational design techniques and machine learning (ML) algorithms, offer a solution to reduce required testing by providing predictions. This paper proposes a deep learning (DL)-based IBCD method for modeling floats' lift-to-drag coefficient ratio (CL/CD), where DL is one of the most powerful ML. The proposed method consists of two phases: hyper-parameter optimization and DL model training and evaluation. A genetic algorithm (GA) is employed in the first phase to explore complex hyper-parameter combinations efficiently. Evaluation of the predicted CL/CD of the floats using the DL model resulted in a satisfactory R-squared of 0.9329 and the lowest mean squared error (MSE) of 0,001536. These results demonstrate the ability of DL model to predict the float's performance accurately and can facilitate further design optimization. Thus, the proposed method can offer a time-efficient and cost-effective solution for predicting float performance, aiding in optimizing floatplane designs and enhancing their functionalities.

show abstract

Section: Results Of Hyper-parameter Optimization (Step 4)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning-based prediction of float model performance in floatplanes: A case study on lift-to-drag coefficient ratio

Fahmi,

Fajar,

Atmaja

et al. 2024

IJ-AI

View full text Add to dashboard Cite

show abstract

“…Additionally, the same experiments will be conducted separately using CNN and LSTM. One of the important factors affecting the performance of CNN and LSTM is the number of layers and filters [29,[46][47][48][49]. The architecture of the constructed CNN includes one input layer, two convolutional layers, two pooling layers, two densely connected layers, and a singleoutput layer, making up a total of six distinct layers.…”

Section: Designed Cnn and Lstm Modelmentioning

confidence: 99%

Classification of Diffusion Constants of Transmitter and Receiver and Distance Between Them Using Mobile Molecular Communication via Diffusion Model

Er,

Isik,

Kuran

et al. 2024

Arab J Sci Eng

View full text Add to dashboard Cite

Molecular communication (MC) holds promise for enabling communication in scenarios where traditional wireless methods may be impractical or ineffective, offering unique capabilities for a range of applications in both natural and engineered systems. In this research, a novel approach to MC is explored, diverging from the standard use of stationary transmitter and receiver models typically found in the field. The study introduces a dynamic MC model, where both the transmitter and receiver are mobile within a diffusion environment. This model operates using a 5-bit system. The key finding is that the mobility of these nanodevices alters their distance, which in turn impacts the likelihood of molecule reception at the receiver. The study employs deep learning techniques, specifically a combination of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks, to categorize the mobility patterns of the receiver (Rx) and transmitter (Tx). By analyzing various mobility rates (Drx and Dtx) and distances between the Tx and Rx, the research successfully identifies the most efficient mobile MC model in terms of molecule reception rates. The use of Linear Support Vector Machine alongside the CNN and LSTM hybrid feature vector resulted in an 87.68% accuracy in predicting diffusion coefficients. Moreover, using a Cubic Support Vector with the same hybrid feature vector, the study achieved an 88.09% accuracy in estimating the distance between the transmitter and receiver. The study concludes that an increase in the mobilities of Rx and Tx correlates with a higher rate of molecule reception.

show abstract

“…For instance, deep learning techniques have been used to predict transonic flow fields 17 and to design airfoils and predict their performance using surrogate modeling 18 . Kasmaiee et al 19 used a multi-layer perceptron (MLP) network to predict the mean lift and drag coefficients of a NACA 0012 airfoil under the deep dynamic stall. Generative adversarial networks (GANs) have also been employed to predict flow fields from sparse data 20 .…”

Section: Introductionmentioning

confidence: 99%

Fast aerodynamics prediction of wedge tail airfoils using multi-head perceptron network

Hasan,

Rahaman,

Zakaria

2023

Preprint

View full text Add to dashboard Cite

The study aimed to predict the flow fields and aerodynamic coefficients of wedge tail airfoils using a multi-head perceptron (MHP) network and classical machine learning (ML) algorithms, including k-nearest neighbors (KNN), decision tree (DT), and random forest (RF). These predictions were based on airfoil sections, x-y grid coordinates, Mach number, and angle of attack, eliminating the need to solve the Navier-Stokes (NS) equations. The database required for training the MHP network and the ML models were generated using the Ansys solver, which solved the NS equations. The results of the models were compared, and it was observed that the MHP network consistently outperformed the others in terms of prediction accuracy. The R2 score of these models on the test data was found to be close to 1. Additionally, the prediction process demonstrated a significant speed improvement of 125 times compared to conventional computational fluid dynamics (CFD) techniques. Once the training was completed, the flow fields and aerodynamic coefficients for a wedge tail airfoil could be obtained within seconds.

show abstract

Optimization of Blowing Jet Performance on Wind Turbine Airfoil Under Dynamic Stall Conditions Using Active Machine Learning and Computational Intelligence

Cited by 16 publications

References 46 publications

Deep learning-based prediction of float model performance in floatplanes: A case study on lift-to-drag coefficient ratio

Deep learning-based prediction of float model performance in floatplanes: A case study on lift-to-drag coefficient ratio

Classification of Diffusion Constants of Transmitter and Receiver and Distance Between Them Using Mobile Molecular Communication via Diffusion Model

Fast aerodynamics prediction of wedge tail airfoils using multi-head perceptron network

Contact Info

Product

Resources

About