Kriging Surrogate-Based Genetic Algorithm Optimization for Blade Design of a Horizontal AxisWind Turbine

Pholdee, Nantiwat; SujinBureerat,; Nuantong, Weerapon

doi:10.32604/cmes.2021.012349

Cited by 8 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A selection process like Roulette Wheel, Tournament, and Rank Based selection methods was used to select the best variable as a parent variable and allowed to mutate to transfer their chromosomes to produce a child variable. The new population generated by the mutation of the parent variable is then used as a new population and new parents were chosen from the generated population and are allowed to mutate to form another group of population [17,18]. This process continues until an optimum solution based on the probabilistic value is reached for the given problem is obtained.…”

Section: Genetic Algorithmmentioning

confidence: 99%

Multi-Objective Optimization with Artificial Neural Network Based Robust Paddy Yield Prediction Model

Muthukumaran¹,

Geetha²,

Ramaraj³

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Agriculture plays a vital role in the food production process that occupies nearly one-third of the total surface of the earth. Rice is propagated from the seeds of paddy and it is a stable food almost used by fifty percent of the total world population. The extensive growth of the human population alarms us to ensure food security and the country should take proper food steps to improve the yield of food grains. This paper concentrates on improving the yield of paddy by predicting the factors that influence the growth of paddy with the help of Evolutionary Computation Techniques. Most of the researchers used to relay on historical records of meteorological parameters to predict the yield of paddy. There is a lack in analyzing the day to day impact of meteorological parameters such as direction of wind, relative humidity, Instant Wind Speed in paddy cultivation. The real time meteorological data collected and analysis the impact of weather parameters from the day of paddy sowing to till the last day of paddy harvesting with regular time series. A Robust Optimized Artificial Neural Network (ROANN) Algorithm with Genetic Algorithm (GA) and Multi Objective Particle Swarm Optimization Algorithm (MOPSO) proposed to predict the factors that to be concentrated by farmers to improve the paddy yield in cultivation. A real time paddy data collected from farmers of Tamilnadu and the meteorological parameters were matched with the cropping pattern of the farmers to construct the database. The input parameters were optimized either by using GA or MOPSO optimization algorithms to reconstruct the database. Reconstructed database optimized by using Artificial Neural Network Back Propagation Algorithm. The reason for improving the growth of paddy was identified using the output of the Neural Network. Performance metrics such as Accuracy, Error Rate etc were used to measure the performance of the proposed algorithm. Comparative analysis made between ANN with GA and ANN with MOPSO to identify the recommendations for improving the paddy yield.

show abstract

Section: Genetic Algorithmmentioning

confidence: 99%

Multi-Objective Optimization with Artificial Neural Network Based Robust Paddy Yield Prediction Model

Muthukumaran¹,

Geetha²,

Ramaraj³

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

show abstract

“…(1) A section of the blades is taken every 25 mm along the radial direction, with a total of 23 sections (2) For each section, using (10) as the objective function and equations ( 7), (11), and ( 13) as the constraint conditions, the axial correction factor a and toroidal correction factors b and F of each blade element are calculated (3) e value of c is solved according to (12) (4) e value of θ is solved according to (8) e solutions of a, b, and F can be obtained using MATLAB. In order to calculate the chord length of each section more accurately, the corresponding lift coefficient is inquired according to the Reynolds number of each section, while the determination of the Reynolds number depends on c; thus, the iterative method is used.…”

Section: Design Principlementioning

confidence: 99%

“…e final design can obtain almost 650 W with a power coefficient of 0.445 at a wind speed of 5.5 m/s, reaching power of 1.18 kW and a power coefficient of 0.40 at a wind speed of 7 m/s. Pholdee et al [11] present an optimization method of new MEXICO blades for a horizontal axis wind turbine in order to maximize the power coefficient, while the design variables are twist angles on the blade radius and rotating axis positions on a chord length of the airfoils. is approach uses a GA based on the Kriging surrogate.…”

Section: Introductionmentioning

confidence: 99%

Optimal Design and Aerodynamic Performance Prediction of a Horizontal Axis Small-Scale Wind Turbine

Yin

Xie

Yao

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The improved aerodynamic design of a horizontal axis small-scale wind turbine blade is crucial to increasing the efficiency and annual energy production of the turbine. One of the vital stages in aerodynamic design is the selection of the airfoil. Using the existing airfoils for a blade design which results in higher turbine characteristics is tedious. Consequently, this paper provides an optimal design strategy for a horizontal axis small-scale wind turbine blade through the multiobjective optimization of the airfoil using the Nondominated Sorting Genetic Algorithm II (NSGA-II). The latter outperforms the other commonly used genetic algorithms (GAs), as well as the Computational Fluid Dynamics (CFD) investigation of the different airfoil types and the wind turbine rotors on the steady or unsteady state aerodynamic performance. An NACA4412 airfoil with higher aerodynamic efficiency is considered as a baseline for the optimization in order to increase the lift coefficient and lift to drag ratio while avoiding excessive variations in the maximum relative thickness and area. The optimized airfoil (NACA4412-OPT) is used as the cross-sectional profile in the design procedure for a novel 1.15 m diameter three-bladed wind turbine rotor at a wind speed of 11.5 m/s, tip speed ratio of 4.65, and pitch angle of 0.2° by the Wilson design method. The two-dimensional analysis demonstrates that the optimized airfoil outperforms the other airfoils yielding the highest lift coefficient and lift to drag ratio, as well as a larger pitch range. The three-dimensional analysis shows that the time-averaged power coefficient value (0.33) of the new wind turbine is almost 26% higher and more stable than that of the original wind turbine while avoiding a high increase of the axial thrust.

show abstract

“…The work presented here focuses on HAWT-type SWTs. The majority of studies of HAWTs are focused on the design and optimization of rotors and blades of turbines [5][6][7][8][9][10][11][12][13]. Some studies [14,15] consider the air profile, blade allowable stress, starting time, and output power.…”

Section: Introductionmentioning

confidence: 99%

Fast Power Coefficient vs. Tip–Speed Ratio Curves for Small Wind Turbines with Single-Variable Measurements following a Single Test Run

Corbalán,

Chiang

2024

Energies

View full text Add to dashboard Cite

Small wind turbines (SWTs) face tremendous challenges in being developed into a more reliable and widespread energy solution, with a number of efficiency, reliability, and cost issues that are yet to be resolved. As part of the development stages of an SWT, testing the resulting efficiency and determining appropriate working ranges are of high importance. In this paper, a methodology is presented for testing SWTs to obtain characteristic performance curves such as Cp (power coefficient) vs. TSR (tip–speed ratio), and torque vs. ω, in a simpler and faster yet accurate manner as an alternative energy solution when a wind tunnel is not available. The performance curves are obtained with the SWT mounted on a platform moving along a runway, requiring only a few minutes of data acquisition. Furthermore, it is only required to measure a single variable, i.e., the generator output voltage. A suitable physics-based mathematical model for the system allows for deriving the desired performance curves from this set of minimal data. The methodology was demonstrated by testing a prototype SWT developed by the authors. The tested prototype had a permanent magnet synchronous generator, but the methodology can be applied to any type of generator with a suitable mathematical model. Given its level of simplicity, accuracy, low cost, and ease of implementation, the proposed testing method has advantages that are helpful in the development process of SWTs, especially if access to a proper wind tunnel is prevented for any reason. To validate the methodology, Cp vs. TSR curves were obtained for an SWT prototype tested under different test conditions, arriving always at the same curve as would be expected. In this case, the test prototype reached a maximum power coefficient (Cp) of 0.35 for wind velocities from 20 to 50 km/h for a TSR of 5.5.

show abstract

Kriging Surrogate-Based Genetic Algorithm Optimization for Blade Design of a Horizontal AxisWind Turbine

Cited by 8 publications

References 15 publications

Multi-Objective Optimization with Artificial Neural Network Based Robust Paddy Yield Prediction Model

Multi-Objective Optimization with Artificial Neural Network Based Robust Paddy Yield Prediction Model

Optimal Design and Aerodynamic Performance Prediction of a Horizontal Axis Small-Scale Wind Turbine

Fast Power Coefficient vs. Tip–Speed Ratio Curves for Small Wind Turbines with Single-Variable Measurements following a Single Test Run

Contact Info

Product

Resources

About