Performance evaluation of sediment ejector efficiency using hybrid neuro-fuzzy models

Sediment transport in the ejector is highly stochastic and non-linear nature, its accurate estimation a complex challenging mission. This study attempts to investigate sediment removal of using newly developed hybrid data-intelligence models. The proposed models are based on hybridization adaptive neuro-fuzzy inference systems (ANFIS) with different metaheuristic algorithms, namely, particle swarm optimization (PSO), genetic algorithm (GA), differential evolution (DE), ant colony (ACO). constructed various related input variables such as concentration, flow depth, velocity, size, Froude number, extraction ratio, number tunnels sub-tunnels, depth at upstream ejector. capacity assessed several statistical evaluation indices. modeling results obtained for studied demonstrated an optimistic finding. Among models, ANFIS-PSO model exhibited best predictability potential maximum correlation coefficient values CC Train = 0.915 CCTest 0.916.