Scholarlink

<p>This study investigates the electro-conductive couple stress fluid flow in an obliquely rotating channel under oscillating thermal boundary conditions using an artificial intelligence (AI) technique, particularly artificial neural network (ANN). The governing partial differential equations are solved analytically, and the effects of key parameters on flow characteristics are systematically evaluated. Results demonstrate that primary velocity is enhanced by stronger magnetic fields, higher oscillation frequencies, and steeper channel angles but diminishes with increasing Hall and rotational parameters. Thermal radiation and oscillation frequency reduce the temperature profile, while wall shear stress exhibits contrasting trends: it increases with the magnetic parameter in the primary flow but decreases in the secondary flow. The ANN model achieves exceptional accuracy (99.97–99.99% for primary flow shear stress, 99.82–99.94% for heat transmission rate, and 99.70–99.88% for mass flow rate predictions), validating its reliability for capturing nonlinear thermo-fluid interactions. These findings have direct applications in rotating machinery thermal management (e.g., turbine cooling, electric motor design), spacecraft thermal control systems, and additive manufacturing processes, where the AI framework enables real-time optimization of complex fluid behavior under dynamic thermal and mechanical loads.</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

Artificial intelligence enhanced modeling of couple stress fluid flow inside an oblique revolving channel with oscillating thermal boundary conditions

  • 期刊论文

  • 发表日期：

    2025年5月20日

查看全文
  • Tilak Kumar Pal,
  • Sanatan Das,
  • Rabindra Nath Jana

摘要

This study investigates the electro-conductive couple stress fluid flow in an obliquely rotating channel under oscillating thermal boundary conditions using an artificial intelligence (AI) technique, particularly artificial neural network (ANN). The governing partial differential equations are solved analytically, and the effects of key parameters on flow characteristics are systematically evaluated. Results demonstrate that primary velocity is enhanced by stronger magnetic fields, higher oscillation frequencies, and steeper channel angles but diminishes with increasing Hall and rotational parameters. Thermal radiation and oscillation frequency reduce the temperature profile, while wall shear stress exhibits contrasting trends: it increases with the magnetic parameter in the primary flow but decreases in the secondary flow. The ANN model achieves exceptional accuracy (99.97–99.99% for primary flow shear stress, 99.82–99.94% for heat transmission rate, and 99.70–99.88% for mass flow rate predictions), validating its reliability for capturing nonlinear thermo-fluid interactions. These findings have direct applications in rotating machinery thermal management (e.g., turbine cooling, electric motor design), spacecraft thermal control systems, and additive manufacturing processes, where the AI framework enables real-time optimization of complex fluid behavior under dynamic thermal and mechanical loads.