Prediction of Sediment Transport in Sewer Using a Combination of Adaptive-Neuro Fuzzy Inference Systems and Genetic Algorithm

In this study, the transportation of sediment in sewer flumes is predicted using a hybrid model. On the other hand, the hybrid model (ANFIS-GA) using Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and Genetic Algorithm (GA) for prediction of the Froude number of three-phase (air, water and sediment) flow is developed. In this study, the genetic algorithm is used to increase the ability of ANFIS by tuning the membership functions and subsequently minimize the error. The genetic algorithm (GA) is a meta-heuristic inspired by the process of natural selection that belongs to the larger class of evolutionary algorithms (EA). Then, the 127 hybrid models were defined using input parameters. For the superior model, the Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) were computed equal to 5.529, 0.315, respectively.