Scholarlink

Background <p>This analysis’s main purpose is to investigate the outcome of melting heating on microorganisms in a two-phase bioconvection flow of a dusty hybrid nanofluid via a sheet with Cattaneo-Christov flux model.</p> Method <p>Using an appropriate similarity transformation, constitutive partial differential equations are transformed into ordinary differential equations. Using reference datasets from numerical calculations, we train and assess the intelligent Bayesian regularized predictive neural network approach to forecast flow solutions under different physical parameter scenarios.</p> Applications <p>This model is valuable in advanced thermal and environmental engineering systems that combine two-phase flows, particulate matter, and microorganism-induced bioconvection. It is used in melting and solidification processes, including phase-change materials, metal casting, and thermal energy storage systems, where dusty hybrid nanofluid improve heat transport. The Cattaneo-Christov flux model’s addition makes it applicable to high-speed thermal transport and conduction of non-Fourier heat in micro- and nanoscale devices.</p> Outcomes <p>When the thermal and solutal relaxation parameters’ values rise, the solutal and thermal distribution improves. Histogram analysis, regression analysis, statistic transition, and Mean square error analysis all show that it is accurate when compared to reference data.</p> Graphical abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Intelligent predictive neural network analysis on two phase bioconvection flow of dusty hybrid nanofluid with Cattaneo Christov flux model and melting phenomena

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月29日

查看全文
  • Ali Raza,
  • Imen Safra,
  • Saba Liaqat,
  • Farkhod Rakhmonov,
  • Munawar Abbas,
  • Durdana Rustamova Farkhad,
  • Abdulbasit A. Darem

摘要

Background

This analysis’s main purpose is to investigate the outcome of melting heating on microorganisms in a two-phase bioconvection flow of a dusty hybrid nanofluid via a sheet with Cattaneo-Christov flux model.

Method

Using an appropriate similarity transformation, constitutive partial differential equations are transformed into ordinary differential equations. Using reference datasets from numerical calculations, we train and assess the intelligent Bayesian regularized predictive neural network approach to forecast flow solutions under different physical parameter scenarios.

Applications

This model is valuable in advanced thermal and environmental engineering systems that combine two-phase flows, particulate matter, and microorganism-induced bioconvection. It is used in melting and solidification processes, including phase-change materials, metal casting, and thermal energy storage systems, where dusty hybrid nanofluid improve heat transport. The Cattaneo-Christov flux model’s addition makes it applicable to high-speed thermal transport and conduction of non-Fourier heat in micro- and nanoscale devices.

Outcomes

When the thermal and solutal relaxation parameters’ values rise, the solutal and thermal distribution improves. Histogram analysis, regression analysis, statistic transition, and Mean square error analysis all show that it is accurate when compared to reference data.

Graphical abstract