Artificial neural network-based study of entropy optimization in Johnson-Segalman nanofluids through a peristaltic channel

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(3)

Published: March 1, 2025

This study includes an artificial neural network (ANN) analysis of irreversibility in Johnson–Segalman nanofluid flow through a peristaltic channel under the influence motile microorganisms, viscous dissipation, and slip effects. The nonlinear partial differential equations are transformed into ordinary by applying lubrication approximation Debye–Hückel transformations with help suitable dimensionless variables. resultant solved analytically using homotopy perturbation method (HPM) linearizing assuming series solution. linear subproblems from HPM successively to find symbolic solution MATLAB utilizing dsolve command. solutions for velocity, temperature, concentration, bioconvection plotted against different physical parameters visualize their behavior profiles. Moreover, data thermal, profiles extracted train ANN model. model is trained Python TensorFlow version 2.17.0., it consists one input layer, two hidden layers (each 64 neurons), output layer. ReLU activation function used layers, Adam optimizer employed our Performance metrics such as mean square error (MSE), regression (R2), histogram, gradient, relative error, absolute computed monitor performance Results show that demonstrates promising accuracy predicting learning momentum findings indicate magnetic field Prandtl number significantly thermal profile, while velocity profile affected Darcy parameter. work has potential applications biomedical engineering, particularly design microfluidic devices targeted drug delivery, also holds relevance environmental engineering.

Language: Английский

---

Magnetohydrodynamics tangent hyperbolic nanofluid flow across a vertical stretching surface using Levengberg-Marquardt back propagation artificial neural networks

Numerical Heat Transfer Part A Applications, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 23

Published: May 10, 2024

This analysis uses the Levenberg-Marquardt back propagation artificial neural networks (LM-BP-ANNs) approach to demonstrate mathematical strategy of for simulation MHD Tangent hyperbolic nanofluid (THNF) flow consisting motile microorganisms through a vertically extending surface. The fluid is being investigated in terms exponential heat source/sink, thermal radiation, and magnetic field. modeled equations are relegated ordinary system differential by substituting similarity variables. ND-solve applied numerically handle generate dataset. Several activities, including testing, verification, training, performed creating scheme various problems using reference data sets. precision LM-BP-ANNs evaluated mean square error, curve fitting error histogram, regression plot. Furthermore, graphs used analyze parameters concentration, momentum, energy profiles. It has been observed that velocity field declines as grows stronger. THNF model energy, mass, momentum tested, authenticated, trained within an average 10−9. accomplish highest accuracy, with target date absolute values 10−4 10−5 range.

Language: Английский

---

Introducing the new arcsine-generator distribution family: An in-depth exploration with an illustrative example of the inverse weibull distribution for analyzing healthcare industry data

Journal of Radiation Research and Applied Sciences, Journal Year: 2024, Volume and Issue: 17(2), P. 100879 - 100879

Published: March 25, 2024

The study is about a novel Arcsin-function based generator of new families distributions. We chose the inverse Weibull distribution as reference to see if could be employed. This helps for developing called Arcsin Weibull. main features suggested have been taken into account. Some indicators used in this class include density function, complete and incomplete moments, average deviation, aging indicators. model's parameters are determined using maximum likelihood method both simulations data analysis. effectiveness model healthcare sector demonstrated by analyzing five sets data, revealing its superior fit compared traditional sine model, which associated with model.

Language: Английский

---

Artificial neural network approach to simulate the impact of concentration in optimizing heat transfer rate on water-based hybrid nanofluid under slip conditions: A regression analysis

Numerical Heat Transfer Part B Fundamentals, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 23

Published: April 1, 2024

The recent era of science depends upon the efficient performance heat transfer rate in several engineering applications for which role nanofluids have a greater impact. Therefore, impact particle concentration optimizing analysis water-based hybrid nanofluid is conducted via an artificial neural network. combined effect oxide nanoparticles such as MgO and TiO2 water performs their effective with various factors involved flow phenomena. magnetized over expanding surface filled porous material shows its noble behavior on properties. Further, it not usual to omit effectiveness dissipative viscous, Joule, Darcy dissipation incorporated energy profile profiles became coupled. designed nonlinear model invokes suitable similarity rules that give rise system ordinary equations non-dimensional form. Afterwards, traditional numerical approach beneficial conduct simulation profiles. optimization obtained by implementation network (ANN) response Nusselt number using factors. regression embedding data proposed this discussion. study describes important outcomes as; increasing slip produces thinning bounding thickness case pure fluid comparing nanofluid. set used fitting than

Language: Английский

---

Effect of Radiation on Casson Hybrid Nano-fluid Flow over an Inclined Surface Using Blasius Rayleigh-Stokes Variable: Application in Solar Aircraft

Engineering Science & Technology, Journal Year: 2024, Volume and Issue: unknown, P. 158 - 179

Published: March 7, 2024

Solar energy is the most important heat source from sun, with photovoltaic cells, solar power plates, lights, and pumping water being widely used. This study looks at analysis a method for increasing efficacy of aircraft by combining nano-technological energy. To enrich research on wings, built investigation transfer employing hybrid nano-fluid past inside parabolic trough collector (PTSC). The thermal referred to as radiative flow. efficiency wings was validated different qualities such porous medium, viscous dissipation, play heating, modelled momentum equations were controlled utilizing Galerkin-weighted residual (GWRM). used two types nano-solid particles, copper (Cu) zirconium dioxide (ZrO2), in ethylene glycol (EG) standard fluid. Various control parameters velocity, temperature outlines, frictional factor, Nusselt number explained shown figures tables. Also, analyses reveal that profile reduces an increase variable conductivity parameters. will be considerable economic value marine engineers, mechanical physicists, chemical others since its application help them improve their operations. findings revealed magnetic term positively impacted Cu-ZrO2/EG nanofluid's distribution.

Language: Английский

---

A new extension of the Gumbel distribution with biomedical data analysis

Journal of Radiation Research and Applied Sciences, Journal Year: 2024, Volume and Issue: 17(4), P. 101055 - 101055

Published: Aug. 7, 2024

In the field of biomedical research, data characteristics often exhibit significant variability, challenging applicability classical Gumbel distribution for modeling. To address this, this paper introduces a novel extension model known as odd beta prime (OBP-Gum) model. Derived from family, new exhibits greater kurtosis compared to traditional distribution. Importantly, proposed is designed capture right-skewed, left-skewed, and nearly symmetric density functions, well increasing, decreasing, constant, upside-down bathtub shapes its hazard rate function, providing excellent curvature features creating flexible statistical models research. We derive fundamental OBP-Gum model, such quantile linear representations, moment generating moments, skewness, kurtosis, incomplete Rényi Tsallis entropies. Parameter estimation conducted using maximum likelihood method. A simulation study demonstrates performance parameters. The empirical findings, based on applications two datasets, suggest that outperforms existing models, particularly in handling extreme observations. Instead relying conventional decision-making, research provides relevant stakeholders with an improved more accurate

Language: Английский

---

A new sine-inspired probability model: Theoretical features with statistical modeling of the music engineering and reliability scenarios

Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 106, P. 288 - 297

Published: July 13, 2024

Language: Английский

---

Data augmentation using SMOTE technique: Application for prediction of burst pressure of hydrocarbons pipeline using supervised machine learning models

Results in Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 103233 - 103233

Published: Oct. 1, 2024

Language: Английский

---

Project Cost Prognostication for Government Buildings Using Feed-Forward Backpropagation Neural Network

Lecture notes in civil engineering, Journal Year: 2025, Volume and Issue: unknown, P. 249 - 259

Published: Jan. 1, 2025

Language: Английский

---

Construction of a novel five-dimensional Hamiltonian conservative hyperchaotic system and its application in image encryption

Soft Computing, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 3, 2025

Language: Английский

---