gbell Learning function along with fuzzy mechanism in prediction of two-phase flow

The integration of the computational fluid dynamics (CFD) and the adaptive network-based fuzzy inference system, known as ANFIS, is investigated for simulating the hydrodynamic in a bubble column reactor. The Eulerian−Eulerian two-phase model is employed as the CFD approach. For the ANFIS technique, a sensitivity analysis is done by varying the number of inputs and the number of membership functions (MFs). The x and z coordinates of the fluid location, the air velocity, and the pressure are considered as the inputs of the ANFIS, while the air vorticity is the output. The results revealed that the ANFIS with all four inputs and the MFs of five achieved the highest intelligence with the regression number close to 1. More specifically, gbell function in the learning framework is used to train all local computing nodes from solving Navier−Stokes equations. In the decision or prediction part, the fuzzy mechanism is used for the prediction of extra nodes that solve, which Navier−Stokes equations did not solve.