Publications
Integrating machine learning and CFD for enhanced trailing edge serration design on a NACA 0012 wind turbine blade
Oct 9, 2025Journal International Journal of Thermofluids
Publisher ELSEVIER
DOI https://doi.org/10.1016/j.ijft.2025.101446
Volume 30
This study combines machine learning (ML) techniques with computational fluid dynamics (CFD) simulations using ANSYS Fluent to investigate the impact of different trailing-edge serration designs on a NACA 0012 airfoil, a commonly used design in wind turbine blades. Building on a fundamental CFD analysis, ML-driven data augmentation—including synthetic data creation, geometric transformations, and noise sensitivity analyses—is employed to enhance and accelerate the design process. The CFD simulations utilize the k-omega SST turbulence model to calculate the lift coefficient (CL) and drag coefficient (CD) over a range of angles of attack (0°–20°). The ML framework evaluates the model's robustness and prediction accuracy under various noise levels and augmented training datasets. Results indicate that the rounded serration design achieves the best lift-to-drag ratio (CL/CD), with approximately a 15 % improvement over the baseline at an angle of attack (α) of 12° In contrast, sharp-edged serrations produce more lift at middle angles but generate increased drag at higher angles. Using hyperparameter-tuned ML models—such as Ridge regression, Random Forest, and a feedforward neural network—improves predictive accuracy and facilitates exploration of the complex design space. This combination of CFD and ML provides a robust method for optimizing wind turbine blade performance, striking a balance between aerodynamic efficiency and computational cost. Unlike previous studies that relied solely on CFD or experiments, this research integrates machine learning with CFD. This dual approach aims not only to analyze the serration geometry but also to optimize it effectively through alternative models and data augmentation. By merging fluid dynamics and machine learning, this approach transforms the design process from trial and error to a data-driven, predictive methodology, marking a significant advance in the aerodynamic design of wind turbine blades.
The effect of titanium dioxide (TiO₂) nanoparticle concentration on the performance of polycrystalline silicon solar cells
Sep 3, 2025Journal Journal of Umm Al-Qura University for Engineering and Architecture
Publisher Springer
DOI https://doi.org/10.1007/s43995-025-00207-z
The performance of polycrystalline silicon solar cells is limited by light reflection, surface contamination, and thermal losses. This has led the industry to focus on researching, developing, and applying new nanocoatings to improve photovoltaic efficiency. This study examines the photovoltaic properties of polycrystalline silicon solar cells by depositing varying concentrations of Titanium dioxide (Tio₂) nanoparticles within a Polymethyl Methacrylate (PMMA) matrix. The materials and methods involve preparing Tio₂/pmma nanocomposites by dispersing Tio₂ nanoparticles into acetone with a colemanite suspension in a PMMA solution. The nanocomposite suspensions are then applied to the surface of the solar cells and allowed to dry. This research aims to evaluate how different Tio₂ loadings affect morphology, optical properties, and electrical performance to optimise efficiency across all Tio₂-based solar cells. SEM analysis confirmed the dispersion of Tio₂ nanoparticles within the PMMA matrix. Lower concentrations of Tio₂ exhibited higher light absorption, consistent with UV-Vis spectroscopy results. The most efficient solar cells containing Tio₂, with a 0.0125 g added layer, achieved an efficiency of 14.4%, attributed to improved light absorption and charge transport. Nonetheless, nanoparticles tend to agglomerate, and higher concentrations of Tio₂ resulted in decreased performance, as evidenced by reduced photocatalytic activity. Properly optimising the concentration of titanium dioxide (TiO₂) is essential for enhancing the efficiency of solar cells.
STUDY ON THE PIPE SIZE AND SURFACE ROUGHNESS EFFECTS ON HYDRAULIC SYSTEM PERFORMANCE
Jun 28, 2024Journal Minar
Publisher Minar
DOI http://dx.doi.org/10.47832/2717-8234.19.%E2%80%8E%E2%80%8F21%E2%80%8F
Issue 2
Volume 6
Significant construction machinery depends on diverse actuators operated by a centralised hydraulic unit. Nevertheless, the presence of lengthy tubes in the hydraulic system gives rise to various difficulties such as friction, leakages, pressure drops, and alterations in flow rate. In order to tackle these concerns, a theoretical analysis has been undertaken. This study focuses on an intricate mathematical model of hydraulics, specifically investigating the impact of various pipe characteristics, including length, diameter, and roughness. The Matlab R2010b software was utilised to examine the precise influence of pipe length on the hydraulic system. We examined many features, including diameter (0.005m, 0.015 m, and 0.025m), pipe length (0.0001m, 25m, 50m, and 100m), and pipe friction factors (0.003, 0.009, and 0.012). The study revealed that increasing the diameter of the pipe (from 0.005m to 0.025m) resulted in an increase in peak gains from 36.2 to 42 dB. This demonstrates that reducing the diameter of pipes results in a hydraulic system that is more stable. A pipe with a shorter length (l = 0.0001 m) leads to an unstable system as a result of overshooting produced by a low damping ratio. In addition, an increase in the friction factor resulted in a decrease in peak gain such as maximum peak gain were 41.2 dB, 40.8 dB at μ = 0.003, and 0.012, respectively. The outcomes of the research indicate that changes in pipe diameters and roughness are ones among other important parameters to be taken into account when considering operating stability of the hydraulic system. These can change and thus influence the dependability as well as performance of all these hydraulic systems Keywords: Hydraulic System, Roughness , Friction, Pipe Diameter, Pipe Length , Stability
Experimental Investigation of the Effects of Grooves in Fe2O4/Water Nanofluid Pool Boiling
May 8, 2024Journal Fluids, MDPI
Publisher MDPI
DOI https://doi.org/10.3390/fluids9050110
Issue 5
Volume 9
In this study, we systematically explored how changing groove surfaces of iron oxide/water nanofluid could affect the pool boiling heat transfer. We aimed to investigate the effect of three types of grooves, namely rectangular, circular, and triangular, on the boiling heat transfer. The goal was to improve heat transfer performance by consciously changing surface structure. Comparative analyses were conducted with deionized water to provide valuable insights. Notably, the heat transfer coefficient (HTC) exhibited a significant increase in the presence of grooves. For deionized water, the HTC rose by 91.7% and 48.7% on circular and rectangular grooved surfaces, respectively. Surprisingly, the triangular-grooved surface showed a decrease of 32.9% in HTC compared to the flat surface. On the other hand, the performance of the nanofluid displayed intriguing trends. The HTC for the nanofluid diminished by 89.2% and 22.3% on rectangular and triangular grooved surfaces, while the circular-grooved surface exhibited a notable 41.2% increase in HTC. These results underscore the complex interplay between groove geometry, fluid properties, and heat transfer enhancement in nanofluid-based boiling. Hence, we thoroughly examine the underlying mechanisms and elements influencing these observed patterns in this research. The results provide important insights for further developments in this area by shedding light on how surface changes and groove geometry may greatly affect heat transfer in nanofluid-based pool boiling systems.
Classification of pistachio by using image processing and deep learning
Dec 28, 2018Publisher International Burasian conference on science, Engineering and lecnnology (burasianscien tech 2018),
Quality is one of the important factors in agricultural products marketing. This study aims to classify pistachio nuts uniformly according to their fields, size, quality, and testing to ensure compliance with certain standard specifications. These products will have advantages in price and sales because they will be easier to store and process standard products for the same property that can be obtained. Traditionally, pistachio nuts are classified via visual inspection of workers, manually. As a result, the classification process is subjected to poor efficiency in terms of time and cost. The most effective method used in grading machines today is image processing. So, it is important to find a fast and accurate system, and this can be achieved through neural networks. The purpose of the research is to create a fast and real time classification system with high accuracy for pistachios or pistachios trashes. This work can be divided into two main parts, segmentation and classification. For image segmentation, local thresholding with average filter were used to isolate the background from the objects in the input images. For image classification, transfer learning to our dataset was used on deep convolutional neural network. The neural network was trained by 1500 images of six types of classification (red pistachio, green pistachio, stone, leaf, unwanted material and branch of pistachio) 250 images for each type, The system was tested with a set of real-time images as well as images stored in the computer, by making a segmentation to the image to make the objects separated in individual images, and then classify each object image by the network. This process was given high accuracy.