This study aims to introduce a novel machine learning feature vector (MLFV) method to bring machine learning to overcome the time-consuming computational fluid dynamics (CFD) simulations for rapidly predicting turbulent flow characteristics with acceptable accuracy.
In this method, CFD snapshots are encoded in a tensor as the input training data. Then, the MLFV learns the relationship between data with a rod filter, which is named feature vector, to learn features by defining functions on it. To demonstrate the accuracy of the MLFV, this method is used to predict the velocity, temperature and turbulent kinetic energy fields of turbulent flow passing over an innovative nature-inspired Dolphin turbulator based on only ten CFD data.
The results indicate that MLFV and CFD contours alongside scatter plots have a good agreement between predicted and solved data with R2 ≃ 1. Also, the error percentage contours and histograms reveal the high precisions of predictions with MAPE = 7.90E-02, 1.45E-02, 7.32E-02 and NRMSE = 1.30E-04, 1.61E-03, 4.54E-05 for prediction velocity, temperature, turbulent kinetic energy fields at Re = 20,000, respectively.
The method can have state-of-the-art applications in a wide range of CFD simulations with the ability to train based on small data, which is practical and logical regarding the number of required tests.
The paper introduces a novel, innovative and super-fast method named MLFV to address the time-consuming challenges associated with the traditional CFD approach to predict the physics of turbulent heat and fluid flow in real time with the superiority of training based on small data with acceptable accuracy.
The hybrid nanofluid flow due to a rotating disk has numerous applications, including centrifugal pumps, paper production, polymers dying, air filtration systems, automobile cooling and solar collectors. This study aims to investigate the convective heat transport and magnetohydrodynamics (MHD) hybrid nanofluid flow past a stretchable rotating surface using the Yamada-Ota and Xue models with the impacts of heat generation and thermal radiation.
The carbon nanotubes such as single-wall carbon nanotubes and multi-wall carbon nanotubes are suspended in a base fluid like water to make the hybrid nanofluid. The problem’s governing partial differential equations are transformed into a system of ordinary differential equations using similarity transformations. Then, the numerical solutions are found with a bvp4c function in MATLAB software. The impacts of pertinent parameters on the flow and temperature fields are depicted in tables and graphs.
Two solution branches are discovered in a certain range of unsteadiness parameters. The fluid temperature and the rate of heat transport are enhanced when the thermal radiation and heat generation effects are increased. The Yamada-Ota model has a higher temperature than the Xue model. Furthermore, it is observed that only the first solution remains stable when the stability analysis is implemented.
To the best of the authors’ knowledge, the results stated are original and new with the investigation of MHD hybrid nanofluid flow with convective heat transfer using the extended version of Yamada-Ota and Xue models. Moreover, the novelty of the present study is improved by taking the impacts of heat generation and thermal radiation.
This paper aims to present a study on stability analysis of Jeffrey fluids in the presence of emergent chemical gradients within microbial systems of anisotropic porous media.
This study uses an effective method that combines non-dimensionalization, normal mode analysis and linear stability analysis to examine the stability of Jeffrey fluids in the presence of emergent chemical gradients inside microbial systems in anisotropic porous media. The study focuses on determining critical values and understanding how temperature gradients, concentration gradients and chemical reactions influence the onset of bioconvection patterns. Mathematical transformations and analytical approaches are used to investigate the system’s complicated dynamics and the interaction of numerous characteristics that influence stability.
The analysis is performed using the Jeffrey-Darcy type and Boussinesq estimation. The process involves using non-dimensionalization, using the normal mode approach and conducting linear stability analysis to convert the field equations into ordinary differential equations. The conventional thermal Rayleigh Darcy number
This study aims to introduce a vision-based model to generate droplets with auto-tuned parameters. The model can auto-adjust the inherent uncertainties and errors involved with the fabrication and operating parameters in microfluidic platform, attaining precise size and frequency of droplet generation.
The photolithography method is utilized to prepare the microfluidic devices used in this study, and various experiments are conducted at various flow-rate and viscosity ratios. Data for droplet shape is collected to train the artificial intelligence (AI) models.
Growth phase of droplets demonstrated a unique spring back effect in droplet size. The fully developed droplet sizes in the microchannel were modeled using least absolute shrinkage and selection operators (LASSO) regression model, Gaussian support vector machine (SVM), long short term memory (LSTM) and deep neural network models. Mean absolute percentage error (MAPE) of 0.05 and R2 = 0.93 were obtained with a deep neural network model on untrained flow data. The shape parameters of the droplets are affected by several uncontrolled parameters. These parameters are instinctively captured in the model.
Experimental data set is generated for varying viscosity values and flow rates. The variation of flow rate of continuous phase is observed here instead of dispersed phase. An automated computation routine is developed to read the droplet shape parameters considering the transient growth phase of droplets. The droplet size data is used to build and compare various AI models for predicting droplet sizes. A predictive model is developed, which is ready for automated closed loop control of the droplet generation.
Flow control has a great potential to contribute to a sustainable society through mitigation of environmental burden. However, the high dimensional and nonlinear nature of fluid flows poses challenges in designing efficient control laws using the control theory. This paper aims to propose a hybrid method (i.e. machine learning and control theory) for feedback control of fluid flows, by which the flow is mapped to the latent space in such a way that the linear control theory can be applied therein.
The authors propose a partially nonlinear linear system extraction autoencoder (pn-LEAE), which consists of convolutional neural networks-based autoencoder (CNN-AE) and a custom layer to extract low-dimensional latent dynamics from fluid velocity field data. This pn-LEAE is designed to extract a linear dynamical system so that the modern control theory can easily be applied, while a nonlinear compression is done with the autoencoder (AE) part so that the latent dynamics conform to that linear system. The key technique is to train this pn-LEAE with the ground truths at two consecutive time instants, whereby the AE part retains its capability as the AE, and the weights in the linear dynamical system are trained simultaneously.
The authors demonstrate the effectiveness of the linear system extracted by the pn-LEAE, as well as the designed control law’s effectiveness for a flow around a circular cylinder at the Reynolds number of ReD = 100. When the control law derived in the latent space was applied to the direct numerical simulation, the lift fluctuations were suppressed over 50%.
To the best of the authors’ knowledge, this is the first attempt using CNN-AE for linearization of fluid flows involving transient development to design a feedback control law.
This paper aims to investigate the effect of different wing height layouts on the aerodynamic performance and flow structure of high-speed train, in a train-wing coupling method with multiple tandem wings installed on the train roof.
The improved delayed detached eddy simulation method based on shear stress transport k-
The wing height layout has a significant effect on the lift, while its influence on the drag is weak. There are three distinctive vortex structures in the flow field: wingtip vortex, train body vortex and pillar vortex, which are influenced by the variation in wing height layout. The incremental wing layout reduces the mixing and merging between vortexes in the flow field, weakening the vorticity and turbulence intensity. This enhances the pressure difference between the upper and lower surfaces of both the train and wings, thereby increasing the overall lift. Simultaneously, it reduces the slipstream velocity at platform and trackside heights.
This paper contributes to understanding the aerodynamic characteristics and flow structure of a high-speed train coupled with wings. It provides a reference for the design aiming to achieve equivalent weight reduction through aerodynamic lift synergy in trains.
The purpose of this study is to establish a novel airfoil icing prediction model using deep learning with geometrical constraints, called geometrical constraints enhancement neural networks, to improve the prediction accuracy compared to the non-geometrical constraints model.
The model is developed with flight velocity, ambient temperature, liquid water content, median volumetric diameter and icing time taken as inputs and icing thickness given as outputs. To enhance the icing prediction accuracy, the model involves geometrical constraints into the loss function. Then the model is trained according to icing samples of 2D NACA0012 airfoil acquired by numerical simulation.
The results show that the involvement of geometrical constraints effectively enhances the prediction accuracy of ice shape, by weakening the appearance of fluctuation features. After training, the airfoil icing prediction model can be used for quickly predicting airfoil icing.
This work involves geometrical constraints in airfoil icing prediction model. The proposed model has reasonable capability in the fast assessment of aircraft icing.
The purpose of this paper is to investigate the impact of mechanical vibration on the heat transfer and pressure drop characteristics of semicircular channel printed circuit heat exchangers (PCHEs), while also establishing correlations between vibration parameters and thermal performance.
By combining experimental and numerical simulation methods, the heat transfer coefficient and pressure drop characteristics of supercritical carbon dioxide (S-CO2) in a semicircular channel with a diameter of 2 mm under vibration conditions were studied. Reinforce the research by conducting computational fluid dynamics studies using ANSYS Fluent 22.0, the experimental results were compared with the numerical simulation results to verify the accuracy of the numerical method.
The use of vibration has the potential to attenuate the degradation of wall heat transfer caused by buoyancy-induced PCHEs on the upward-facing surface. The heat transfer enhancement (HTE) was maximized by an increase of 18.2%, while the pressure drop enhancement (PDE) was elevated by over 25-fold. The capacity to enhance the heat exchange between S-CO2 and channel walls through increasing vibration intensity is limited, indicating maximum effectiveness in improving thermal performance.
Conducting heat transfer experiments on PCHEs with mechanical vibration enhancement and verifying the accuracy of the vibration numerical model. The relation based on the dimensionless factor is derived. To provide theoretical support for using vibration to enhance the heat transfer capability of PCHEs.
This study aims to explore a novel model that integrates the Kairat-II equation and Kairat-X equation (K-XE), denoted as the Kairat-II-X (K-II-X) equation. This model demonstrates the connections between the differential geometry of curves and the concept of equivalence.
The Painlevé analysis shows that the combined K-II-X equation retains the complete Painlevé integrability.
This study explores multiple soliton (solutions in the form of kink solutions with entirely new dispersion relations and phase shifts.
Hirota’s bilinear technique is used to provide these novel solutions.
This study also provides a diverse range of solutions for the K-II-X equation, including kink, periodic and singular solutions.
This study provides formal procedures for analyzing recently developed systems that investigate optical communications, plasma physics, oceans and seas, fluid mechanics and the differential geometry of curves, among other topics.
The study introduces a novel Painlevé integrable model that has been constructed and delivers valuable discoveries.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：