Intelligent Bayesian regularization‐based solution predictive procedure for hybrid nanoparticles of AA7072‐AA7075 oxide movement across a porous medium

Abstract

The research community has shown great interest for investigation in the nanofluids models involving Aluminum Alloys AA7072 and AA7072 +AA7075 due to their advantageous impact on heat transfer, physical and mechanical characteristic exploiting in broad engineering applications such as manufacturing of spacecraft, aircraft parts and building testing. The hybrid nanomaterial AA7072-AA7075 based fluidic system is investigated in this paper using an artificial neural network with Bayesian regularization scheme (ANNs-BRS). The derived partial differential equations (PDEs) are transformed into ordinary differential equations system ODEs and obtained the reference datasets for the estimated solution dynamics of hybrid nanofluidic system. For prominent parameters, the influence of flow on the temperature distribution and velocity plot are investigated. The performance on 80% training samples, 5% testing and 15% validation dataset for ANNs-BRS is well-established in terms of error histogram plots, regression analysis, and MSE based statistics. The results for entropy generation, Eckert number Ec, magnetic interaction parameter M, suction parameter S, and heat generation parameter 𝑄 are also discussed. The results show that the Eckert number Ec has the effect of slowing down the rate of heat transfer while increasing the temperature and increases in suction parameter causes decrease in temperature while increase in temperature profile due to enhancement of suction parameter.

Numerical assessment of irreversibility in radiated Sutterby nanofluid flow with activation energy and Darcy Forchheimer

“…Bayesian regularization networks is implemented to explore the features of nanofluid flows considering various effects by Awan et al 21 , 22 . Ahmad et al 23 deliberated Maxwell nanomaterial flow by permeable rotating frame with heat transfer analysis. Flow behavior of radiative MHD Maxwell nanoliquid considering viscous dissipation effects is investigated by Hsiao 24 .…”

Generating Mathematical Expressions for Estimation of Atomic Coordinates of Carbon Nanotubes Using Genetic Programming Symbolic Regression

“…In addition to the GPSR, future work regarding this dataset will be to employ various other AI algorithms, such as Bayesian regularization networks [23][24][25][26][27][28][29], ensemble methods [30], multi-layer perceptron, and XGBoost [31], among others, and compare their performance with the GPSR estimation performance.…”