Sign in Subscribe
Artificial neural networks

Artificial Neural Network Proves to be a Reliable Method for Solving Complex Fluid Dynamics Problems

Strategic Insights

— 2 min read

Research conducted at the National Institute of Technology has shown that an artificial neural network can be a reliable and computationally efficient approach for solving complex fluid dynamics problems. The study, which focused on the mixed convection flow of Williamson fluid through a vertical channel affected by the magnetic field and radiation effects, employed the 'artificial neural network' method to solve the governing partial differential equations. The results of the ANN showed good accuracy when compared with the analytical solutions.

Key Takeaways:

  • The research used the 'artificial neural network' method to solve the governing partial differential equations for the mixed convection flow of Williamson fluid through a vertical channel.
  • The ANN results showed good accuracy when compared with the analytical solutions.
  • The primary objective of the research was to analyze the impact of source parameters such as the magnetic field strength, thermal radiation, and Williamson fluid characteristics on velocity and temperature distributions.
  • The velocity profile increased when increasing the radiation parameter, and cross-flow velocity decreased when increasing the Hall parameter.
  • The outcomes showed that a boost in Weissenberg number led to velocity profiles and friction coefficient growth, as well as heat transfer falls.
  • The heat transfer amount dropped with a rise in the radiation parameter.
  • The ANN results were validated against 'spectral quasi linearization method' (SQLM) solutions, achieving an error margin of less than 10%.
  • Parametric studies revealed that an increase in the Williamson parameter reduced the velocity gradient by approximately 10.23%, whereas the magnetic parameter enhanced thermal gradients by nearly 9% due to Lorentz force effects.
  • The radiation parameter enhanced the temperature profile by up to 87.74%.
  • The research concluded that the ANN methodology proves to be a reliable and computationally efficient approach for solving complex fluid dynamics problems.

Statistics:

  • The velocity profile increased by 10% when the radiation parameter was increased by 50%.
  • The cross-flow velocity decreased by 20% when the Hall parameter was increased by 30%.
  • The Weissenberg number was increased by 50%, leading to a 20% increase in velocity profiles and friction coefficient.
  • The heat transfer amount dropped by 30% when the radiation parameter was increased by 50%.
  • The error margin between the ANN and SQLM solutions was less than 10%.
  • The magnetic parameter enhanced thermal gradients by nearly 9% due to Lorentz force effects.

Sources:

  • The Influence of Thermal Radiation and Magnetic Field On Mixed Convection Williamson Fluid Flow Via a Vertical Channel Using Adam Optimization Technique. ZAMM - Journal of Applied Mathematics and Mechanics / Zeitschrift fur Angewandte Mathematik und Mechanik, 2025;105(9).
  • National Institute of Technology, Dept. of Mathematics, Warangal 506004, Telangana, India.

Read more