Scientific Reports (Nov 2024)

Artificial intelligence neural network and fuzzy modelling of unsteady Sisko trihybrid nanofluids for cancer therapy with entropy insights

  • A. Divya,
  • Thandra Jithendra,
  • Muhammad Jawad,
  • Taoufik Saidani,
  • Qasem M. Al-Mdallal,
  • Abeer A. Shaaban

DOI
https://doi.org/10.1038/s41598-024-79495-9
Journal volume & issue
Vol. 14, no. 1
pp. 1 – 30

Abstract

Read online

Abstract The main objective of the current endeavor is to monitor hypothetical processes utilizing a Sisko tri-hybrid fluid over a rotating disk with entropy generation suspended in Darcy-Forchheimer porous medium. Electro Magneto Hydro Dynamics (EMHD), non-linear thermal radiation and exponential and thermal- space dependent heat source/sink coefficients are considered with the intent of conceiving an Runge-Kutta-Fehlberg method with shooting procedures integrated with a combination of an Adaptive Neuro-Fuzzy Inference System (ANFIS) and Reptile Search Algorithm (RSA). Then, ANFIS-RSA, is used to predict the Nusselt number, skin friction co-efficient in radial and tangential velocities. Reliable self-similarity variables have reduced a non-linear partial differential set of equations into an ordinary differential equation. According to the empirical evidence, Sisko fluid parameter rises the radial velocity whereas for magnetic field and Darcy-Forchheimer the azimuthal and axial velocities visualizations decreasing trend, respectively. The entropy generation and Bejan number rises for electric and radiation effects. Also, ANFIS-RSA indicates that the model attained a high level of precision in terms of radial velocity (98.13%), tangential velocity (98.18%) and Nusselt number (98.91%). Thus, the longer rendering of the nanoparticles used here might, makes them potentially helpful for regulating the therapeutic impact in the management and treatment of cancer.

Keywords