Application of a Neuro-Fuzzy GMDH Model for Predicting the Velocity at Limit of Deposition in Storm Sewers

The velocity at limit of deposition, namely, the velocity below which the sediments start to form stationary deposits on the pipe invert, plays a key role in designing an effective storm sewer system. In fact, an accurate evaluation of the aforesaid velocity permits to prevent the formation of sediment deposits in the pipe, and, consequently, a decreasing of the hydraulic capacity of the same pipe. Nowadays, different methods based on artificial intelligence are applied to analyze and solve problems of scientific and practical interest, among which the analysis of sediment transport mechanism in clean storm sewer networks. In this study, neuro-fuzzy based group method of data handling (NF-GMDH), an adaptive learning network, has been utilized to predict the velocity at limit of deposition in partially-filled circular storm sewer networks under noncohesive bed load sediment transport and clean pipe conditions. The NF-GMDH network has been developed using the particle swarm optimization (PSO). Four different dimensionless groups have been used as input parameters to evaluate the dimensionless velocity at limit of deposition (or, equivalently, the densimetric particle Froude number at limit of deposition) through the NF-GMDH-PSO model. A published experimental data sets were collected from the literature to train and test the adaptive learning network used in this study. The performances of training and testing stages for NFGMDH-PSO have been evaluated using specific statistical indexes. The results showed that NF-GMDH-PSO model is able to give more accurate predictions of the velocity at limit of deposition compared with those obtained using semiempirical equations.