Adaptive-Network-Based Fuzzy Inference System Analysis to Predict the Temperature and Flow Fields in a Lid-Driven Cavity

Abstract

Heat transfer behavior in a 2-D square lid-driven cavity has been studied for various pertinent Reynolds and Rayleigh numbers. The lattice Boltzmann method, a numerical tool based on the particle distribution function is applied to simulate a thermal fluid flow problem. Bhatnagar-Gross-Krook (BGK) is combined with the double population thermal Lattice Boltzmann model to solve mixed convection in a square cavity. An adaptive-network-based fuzzy inference system (ANFIS) method is trained and validated using BGK Lattice Boltzmann model results. The results show that the trained ANFIS model successfully predicts the temperature and flow fields in a few seconds with acceptable accuracy.