Search

In the current study, three machine learning (ML) models, i.e. Gaussian process regression (GPR), generalized regression neural network (GRNN), and multigene genetic programming (MGGP), were developed for predicting the discharge coefficient (Cd) of a radial gate under two different flow conditions, i.e. free and submerged. The modeling development of the flow and geometry input variables for the Cd was determined based on statistical correlations. We also performed a sensitivity analysis of the input variables for the Cd. The modeling results indicated that the developed ML models attained acceptable predictable performance; however, the prediction accuracy of the models was better under the free flow condition. In quantitative terms, the minimum root mean square error (RMSE) value was 0.010 using the GPR model and 0.019 using the MGGP model for the submerged and free flow conditions, respectively. The sensitivity analysis evidenced that the ratio of the gate opening height to the depth of water in the upstream (W:Yo) was the influential variable for the Cd under the free flow condition, whereas the ratio of the depth of water in the upstream to the depth of water in downstream (Yo:YT) was the influential variable for the Cd under the submerged flow condition. [ABSTRACT FROM AUTHOR]

The scour phenomena around vertical piles in oceans and under waves may influence the structure stability. Therefore, accurately predicting the scour depth is an important task in the design of piles. Empirical approaches often do not provide the required accuracy compared with data mining methods for modeling such complex processes. The main objective of this study is to develop three data-driven methods, locally weighted linear regression (LWLR), support vector machine (SVR), and multivariate linear regression (MLR) to predict the scour depth around vertical piles due to waves in a sand bed. It is the first effort to develop the LWLR to predict scour depth around vertical piles. The models simulate the scour depth mainly based on Shields parameter, pile Reynolds number, grain Reynolds number, Keulegan–Carpenter number, and sediment number. 111 laboratory datasets, derived from several experimental studies, were used for the modeling. The results indicated that the LWLR provided highly accurate predictions of the scour depths around piles (R = 0.939 and RMSE = 0.075). Overall, this study demonstrated that the LWLR can be used as a valuable tool to predict the wave-induced scour around piles. [ABSTRACT FROM AUTHOR]

Exact evaluation of scour depth around piers under debris accumulation is crucial for the safe design of pier structures. Experimental studies on scouring around pier bridges with debris accumulation have been conducted to estimate the maximum scour depth using various empirical relationships. However, due to the oversimplification of a complex process, the proposed relationships have not always been able to accurately predict the pier scour depth. This research proposes linear genetic programming (LGP) approach as an extension of the genetic programming to predict the scour depth around bridge piers. Among the artificial intelligence techniques, LGP and locally weighted linear regression (LWLR) models have not been used to predict the scour depth at bridge piers. Literature experimental data were collected and used to develop the models. The performance of the LGP method was compared with gene-expression programming, LWLR, multilinear regression and empirical equations using rigorous statistical criteria. The correlation coefficient (R) and the root mean squared error (RMSE) were (R = 0.962, RMSE =0.31) and (R = 0.885, RMSE =0.542) for the LGP and LWLR, respectively. The results demonstrated the superiority of the LGP method for increasing the accuracy of the predicted scour depth in comparison with the other models. [ABSTRACT FROM AUTHOR]