Scholarlink

<p>Present study explores the convective flow of ternary-hybrid nanofluids (TNF) composed of Copper (Cu), Molybdenum disulfide (MoS<sub>2</sub>) and Silver (Ag) dispersed traditional base fluid Water (H<sub>2</sub>O) around stretchable cylindrical veins for hyperthermia cancer therapy. The research employs an Artificial intelligence-based machine learning algorithm of Python environment with non-monotonic Swish activation and an Adaptive Moment Estimation (Adam) optimizer for governing ODEs, which obtained through similarity shift of PDEs. The impacts of curvature, mixed convection, momentum to thermal diffusivity ratio, and ratio of kinetic energy to enthalpy are examined against flow behavior, temperature changes, skin drag and convective-conductive heat transfer ratio. The investigation offers enhanced thermal conductivity and efficient thermal exchange up to 20% with precise temperature control for effective cancer treatment. Also, the study includes predicted results with enhanced domain to forecast results. The novelty here is a combination of machine learning model proposing new applications of a combination of high-tech materials and cutting-edge time efficient and cost-effective computing strategies in improving performance and accuracy.</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

AI-driven analysis of buoyancy-convective flow of ternary-hybrid nanofluid in a porous medium over stretching cylinder

  • 期刊论文

  • 发表日期：

    2025年8月1日

查看全文
  • Hamid Qureshi

摘要

Present study explores the convective flow of ternary-hybrid nanofluids (TNF) composed of Copper (Cu), Molybdenum disulfide (MoS2) and Silver (Ag) dispersed traditional base fluid Water (H2O) around stretchable cylindrical veins for hyperthermia cancer therapy. The research employs an Artificial intelligence-based machine learning algorithm of Python environment with non-monotonic Swish activation and an Adaptive Moment Estimation (Adam) optimizer for governing ODEs, which obtained through similarity shift of PDEs. The impacts of curvature, mixed convection, momentum to thermal diffusivity ratio, and ratio of kinetic energy to enthalpy are examined against flow behavior, temperature changes, skin drag and convective-conductive heat transfer ratio. The investigation offers enhanced thermal conductivity and efficient thermal exchange up to 20% with precise temperature control for effective cancer treatment. Also, the study includes predicted results with enhanced domain to forecast results. The novelty here is a combination of machine learning model proposing new applications of a combination of high-tech materials and cutting-edge time efficient and cost-effective computing strategies in improving performance and accuracy.