Artificial intelligence models for prediction of the aeration efficiency of the stepped weir. (March 2019)

• Record Type: Journal Article
• Authors: Sattar, Ahmed A.; Elhakeem, Mohamed; Rezaie-Balf, Mohammad; Gharabaghi, Bahram; Bonakdari, Hossein
• Is Part Of: Flow measurement and instrumentation. Volume 65(2019)
• Page Start: 78
• Page End: 89
• Publication Date: 2019-03
• Subjects: ANFIS neuro-fuzzy inference system -- ANN artificial neural networks -- Cp Mallows' coefficient -- Cu, CD, Cs upstream, downstream and saturation dissolved oxygen concentrations -- D Diffusivity -- E transfer efficiency -- E20 transfer efficiency for 20 °C -- EPR evolutionary polynomial regression -- EPR-MOGA evolutionary polynomial regression- multi-objective genetic algorithm -- Fr Froude number -- G acceleration due to gravity -- fmaxxi maximum of the predicted output -- fminxi minimum of the predicted output -- hc flow critical depth -- H total weir height -- H step height -- K explanatory variables -- k and k' regression lines -- l weir step length -- MT model tree -- N weir number of steps -- n sample size -- O observed aeration efficiency -- O¯ mean of the observed values -- P predicted aeration efficiency -- P¯ mean of the predicted values -- q discharge per unit width -- R correlation coefficient -- Rm cross-validation coefficient -- RMAE relative mean absolute error -- RMSE root mean square error -- RSSp residual sum of squares -- Re Reynolds number -- Ro2, Ro′2 squared correlation coefficients through the origin -- SDR standard deviation reduction -- SVM support vector machine -- T temperature -- X1 × X2 input space by the M5 model tree -- α stepped weir slope -- a0 Bias -- μ Viscosity -- ρ density -- σ surface tension; Stepped weir -- Aeration efficiency -- Model -- Flow; Fluid dynamic measurements -- Periodicals; Flow meters -- Periodicals; Fluides, Dynamique des -- Mesure -- Périodiques; Débitmètres -- Périodiques; 681.2805
• DOI: 10.1016/j.flowmeasinst.2018.11.017
• Languages: English
• ISSNs: 0955-5986

Abstract

Abstract: Stepped weir is a commonly used hydraulic structure in water treatment plants to enhance the air-water transfer of oxygen or nitrogen and volatile organic components. The flow regimes on stepped weir are classified into nappe, transition and skimming flow. This study presents the novel application of artificial intelligence methods to evaluate the aeration efficiency over stepped weir for the three flow regimes. Two methods were adopted in this study, namely, the evolutionary polynomial regression (EPR) and the M5 model tree (M5 MT). A total of 151 laboratory experimental data sets were collected from the literature to train and test the artificial intelligence models. The Mallow's coefficient CP was used to determine the effective variables affecting aeration efficiency. It was found that weir steps number, slope, the flow Reynolds number, and the ratio of the critical flow depth to the step height are the most important variables providing the lowest Cp . Both the EPR and M5 MT methods provided satisfactory predictions for the aeration efficiency. The two methods have high values of correlation coefficient R > 0.93 and low values for the root mean square error RMSE< 0.052 and relative mean absolute error RMAE< 0.065. However, the EPR method has an advantage over the M5 MT method that it provides one equation for each regime, while the M5 MT method provides a number of equations for each regime. This will make the equations of the EPR method more attractive to the practitioners compared to the equations of the M5 MT method. It was found that the equations obtained from artificial intelligence methods in this study perform better than the currently existing equations in the litrature obtained from regressive methods. Highlights: A new empirical equation for the prediction of the aeration efficiency of stepped weir is developed. Experimental data covering a broad range of hydraulic conditions are collected. Sensitivity of the developed models for various predictors is quantified.