Machine learning approach on chemical species and thermal management in Ellis’s fluid considering hall currents and thermal jumps across sphere via Taguchi analysis

Sohail, Muhammad; Nazir, Umar; Abodayeh, Kamaleldin; Mahariq, Ibrahim

doi:10.1177/23977914261429835

Machine learning approach on chemical species and thermal management in Ellis’s fluid considering hall currents and thermal jumps across sphere via Taguchi analysis

Sohail M., Nazir U., Abodayeh K., Mahariq I.

Proceedings of the Institution of Mechanical Engineers, Part N: Journal of Nanomaterials, Nanoengineering and Nanosystems, 2026 (ESCI, Scopus)

Nəşrin Növü: Article / Article
Nəşr tarixi: 2026
Doi nömrəsi: 10.1177/23977914261429835
jurnalın adı: Proceedings of the Institution of Mechanical Engineers, Part N: Journal of Nanomaterials, Nanoengineering and Nanosystems
Jurnalın baxıldığı indekslər: Emerging Sources Citation Index (ESCI), Scopus
Açar sözlər: Ellis’s fluid, Hall currents, heat transfer, machine learning approach, non-Fourier’s law, Taguchi method
Adres: Yox

Qısa məlumat

The schemed article explores the robust application of machine learning (ML) approach to investigate the chemical species demeanor along with thermal management toward the Ellis’s Fluid, specifically focusing on the characteristics of Hall current together with thermal jumps within a sphere. The fundamental focus relies on the understanding of how these considered factors affects thermal transportation as well as chemical reactions across the fluid. A comprehensive technique is utilized, invoking Taguchi analysis in order to optimize the constraints affecting the performance of the system, like fluid properties, external magnetic field along with thermal conductivity. The contemplated machine learning (ML) model is disciplined to predict the chemical as well as thermal behavior exposed to diverse factors. Under these terms, insights within the optimal configurations specified by efficacious thermal management and also species distribution is provided. The outcomes illustrate the machine learning potential in improving the design as well as systems optimization considering magnetohydrodynamic and also thermal transportation offering a novel technique for dealing complex challenges of fluid dynamics within the engineering applications. Further, the outcomes are summarized and showcased exemplary outcomes through graphical format and also shown in tabular form for clarity.