Pareto genetic design of group method of data handling type neural network for prediction discharge coefficient in rectangular side orifices

Ebtehaj, Isa; Bonakdari, Hossein; Khoshbin, Fatemeh; Azimi, Hamed

doi:10.1016/j.flowmeasinst.2014.10.016

Cited by 75 publications

(24 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(17)) and models 2e5 were presented to investigate the effects of not considering each of the dimensionless parameters on the outcomes of predicting the discharge coefficient. The table shows that not considering each of the parameters presented in equation (16) leads to the proposed models based on GMDH becoming less accurate. The table indicates that the effects of the F 1 and p/y 1 parameters are almost equal, such that not using these parameters in the model to estimate the discharge coefficient results in an increase in the relative error by 3% and the RMSE amount becoming 1.34 times greater.…”

Section: Resultsmentioning

confidence: 99%

GMDH-type neural network approach for modeling the discharge coefficient of rectangular sharp-crested side weirs

Ebtehaj

Bonakdari

Zaji

et al. 2015

Engineering Science and Technology, an International Journal

Self Cite

View full text Add to dashboard Cite

a b s t r a c tEstimating the discharge coefficient using hydraulic and geometrical specifications is one of the influential factors in predicting the discharge passing over a side weir. Taking into account the fact that existing equations are incapable of estimating the discharge coefficient well, artificial intelligence methods are used to predict it. In this study, Group Method of Data Handling (GMDH) was used for the purpose of predicting the discharge coefficient in a side weir. The Froude number (F 1 ), weir dimensionless length (b/B), ratios of weir length to depth of upstream flow (b/y 1 ) and weir height to its length (p/y 1 ) were taken as input parameters to express a new model for predicting the discharge coefficient. Two different sets of laboratory data were used to train the artificial network and test the new model. Different statistical indexes were used to evaluate the performance of the GMDH model presented for two states, training and testing. The results indicate that the proposed model predicts the discharge coefficient precisely (MAPE ¼ 5.263 & RMSE ¼ 0.038) and this model is more accurate in predicting than the feed-forward neural network model and existing nonlinear regression equations.

show abstract

Section: Resultsmentioning

confidence: 99%

GMDH-type neural network approach for modeling the discharge coefficient of rectangular sharp-crested side weirs

Ebtehaj

Bonakdari

Zaji

et al. 2015

Engineering Science and Technology, an International Journal

Self Cite

View full text Add to dashboard Cite

show abstract

“…These indexes only exhibit the difference between the experimental and predicted values but not the forecast error distribution using MLP and MLP-DT; therefore, other indexes including absolute relative error (ARE) and threshold statistics (TS) are employed (Ebtehaj et al, 2015). The TS x error distribution index represents the predicted values for x% of the anticipated data.…”

Section: Goodness Of Fitmentioning

confidence: 99%

Design of a new hybrid artificial neural network method based on decision trees for calculating the Froude number in rigid rectangular channels

Ebtehaj

Bonakdari

Zaji

et al. 2016

Journal of Hydrology and Hydromechanics

Self Cite

View full text Add to dashboard Cite

A vital topic regarding the optimum and economical design of rigid boundary open channels such as sewers and drainage systems is determining the movement of sediment particles. In this study, the incipient motion of sediment is estimated using three datasets from literature, including a wide range of hydraulic parameters. Because existing equations do not consider the effect of sediment bed thickness on incipient motion estimation, this parameter is applied in this study along with the multilayer perceptron (MLP), a hybrid method based on decision trees (DT) (MLP-DT), to estimate incipient motion. According to a comparison with the observed experimental outcome, the proposed method performs well (MARE = 0.048, RMSE = 0.134, SI = 0.06, BIAS = -0.036). The performance of MLP and MLP-DT is compared with that of existing regression-based equations, and significantly higher performance over existing models is observed. Finally, an explicit expression for practical engineering is also provided.

show abstract

“…Additionally, Ebtehaj et al (2015) simulated the discharge coefficient of rectangular side orifices using group method of data handling. They carried out a sensitivity analysis in order to identify effective input parameters.…”

Section: Introductionmentioning

confidence: 99%

Optimization of ANFIS network using firefly algorithm for simulating discharge coefficient of side orifices

et al. 2019

View full text Add to dashboard Cite

Side orifices are installed on side walls of the main channel to regulate and measure the flow. Generally, discharge coefficient is the most important hydraulic parameter of side orifices. In this study, using ANFIS and firefly algorithm, discharge coefficient of rectangular and circular side orifices was simulated. Firstly, effective parameters were defined then six ANFIS and ANFIS-FA models were introduced. Monte Carlo simulations were utilized to survey the ability of numerical models, and the k-fold cross-validation approach was used to validate numerical results. Then, a sensitivity analysis was employed to introduce the superior model. The superior model predicted discharge coefficient with reasonable accuracy. This model estimated discharge coefficient in terms of all input variables. For example, for ANFIS model, R and SI were computed 0.832 and 0.029, respectively. In addition, for the hybrid model, RMSE, MARE and SI were calculated as 0.017, 0.017 and 0.027, respectively. Additionally, the ratio of width of the main channel to the side orifice diameter (B/D) was identified as the most effective parameter.

show abstract

Pareto genetic design of group method of data handling type neural network for prediction discharge coefficient in rectangular side orifices

Cited by 75 publications

References 39 publications

GMDH-type neural network approach for modeling the discharge coefficient of rectangular sharp-crested side weirs

GMDH-type neural network approach for modeling the discharge coefficient of rectangular sharp-crested side weirs

Design of a new hybrid artificial neural network method based on decision trees for calculating the Froude number in rigid rectangular channels

Optimization of ANFIS network using firefly algorithm for simulating discharge coefficient of side orifices

Contact Info

Product

Resources

About