Simulation of an improved cyclone was carried out by means of Artificial Neural Networks (ANNs), adaptive-network-based fuzzy inference system (ANFIS), and hybrid ANN-Genetic Algorithm (GA). The apparatus consists of two cyclones coupled with a specially designed cylindrical chamber, which includes a rotating tube inside with air-impinging nuzzles drilled on the peripheral surface of the tube. The chamber includes a tube with nozzles on its peripheral surface from which jet-impingement flow throws the particles nearer to wall of the chamber. Efficiency of the jet-impingement chamber, as a function of flow rate on the feed, recycle, jet-impingement along with jet-impingement tube rotational speed, has been tested. ANN, ANFIS, and hybrid ANN-GA are capable to accurately capture the non-linear characteristics of the chamber performance.

Keywords