Application of improved neuro-fuzzy GMDH to predict scour depth at sluice gates

Abstract

An improved neuro-fuzzy based group method of data handling using the particle swarm optimization (NF-GMDH-PSO) is developed as an adaptive learning network to predict the localized scour downstream of a sluice gate with an apron. The input characteristic parameters affecting the scour depth are the sediment size and its gradation, apron length, sluice gate opening, and the flow conditions upstream and downstream of the sluice gate. Six non-dimensional parameters were yielded to define a functional relationship between the input and output variables. The training and testing of the NF-GMDH network are performed using published scour data from the literature. The efficiency of the training stages for the NF-GMDH-PSO is investigated. The testing results for the NF-GMDH network are compared with the traditional approaches based on regression method. A sensitivity analysis is carried out to assign the most significant parameter for the scour prediction. The results showed that the NF-GMDH-PSO network produced lower error in scour prediction than all other models.

Evaluation of GMDH networks for prediction of local scour depth at bridge abutments in coarse sediments with thinly armored beds

“…In GSA, a set of agents called masses are introduced to find the optimum solution by simulation of Newtonian laws of gravity and motion (Rashedi et al, 2011;Li and Zhou, 2011;Azamathulla, 2013a, 2013b;Najafzadeh and Lim, 2014). To describe the GSA consider a system with s masses in which the position of the ith mass is defined as follows: …”

Estimation of scour downstream of a ski-jump bucket using the multivariate adaptive regression splines

“…Due to high cost of experiments and de ciency in laboratory studies due to simpli cations and limit range of measured parameters, researchers attempt to use the mathematical approaches for modeling and predicting the scour depth at downstream of ip buckets. In the eld of mathematical modeling, using both of CFD and soft computing techniques was reported by Xiao et al [11].Nowadays, by advancing the soft computing techniques in the most areas related to hydraulic engineering, investigators have tried to use these techniques for predicting the scouring phenomena [12][13][14][15][16][17][18][19], speci cally scour depth at downstream of ip bucket. In this regard, using the Arti cial Neural Networks (ANNs), Genetic Programming (GP), Support Vector machine and M5 Model Tree, Group Method of Data Handling (GMDH), and Adaptive Neuro Fuzzy Inference System (ANFIS) can be mentioned [20][21][22][23][24][25][26][27][28][29][30][31][32].…”

Development of group method of data handling based on genetic algorithm to predict incipient motion in rigid rectangular storm water channel

“…Due to the availability and the capacity of soft computing in solving complex problems, its methods have been widely applied by di erent disciplines such as hydrology, hydraulic, and sediment transport [12][13][14][15][16][17][18][19][20][21]. Group Method of Data Handling network is one of the self-organized methods amongst soft computing methods based on arti cial intelligence, capable of solving di erent problems in extremely complex nonlinear systems [22][23][24][25]. The GMDH method has been used to recognize behavior of nonlinear systems in di erent subjects in hydraulic such as friction factor in pipeline [26], scour depth [27][28][29], discharge condent [30,31], ow discharge in straight compound channels [32,33], basin sediment yield [34], and longitudinal dispersion in water networks [35].…”