Modeling of effluent quality parameters in a submerged membrane bioreactor with simultaneous upward and downward aeration treating municipal wastewater using hybrid models

Abstract

2015): Modeling of effluent quality parameters in a submerged membrane bioreactor with simultaneous upward and downward aeration treating municipal wastewater using hybrid models, Desalination and Water Treatment, A B S T R A C TThis research was an effort to develop hybrid multilayer perceptron and radial basis function artificial neural network-genetic algorithm (MLPANN-GA and RBFANN-GA) models to accurately predict effluent biochemical oxygen demand (BOD), chemical oxygen demand (COD), total nitrogen (TN), and total phosphorus (TP) in a submerged membrane bioreactor. The input variables of the networks were influent BOD, influent COD, influent TN or influent TP, sludge retention time (SRT), mixed liquor suspended solid, membrane permeability, and transmembrane pressure. Training procedures of all effluent quality parameters were successful for both the MLPANN-GA and RBFANN-GA models. The training and testing models showed an almost perfect match between the experimental and predicted values. Based upon the statistical analysis, results indicated that there is a very little difference between predicted and experimental values of the effluent BOD, COD, TN, and TP. The predicted and experimental values of the effluent concentrations gave a very low root mean squared error and a high coefficient of determination very close to one demonstrated high accuracy of these models to predict output variables. It became clear that the models based on the genetic algorithm (GA) were much better than those models without GA from the viewpoint of the achievement of an accurate prediction of the effluent BOD, COD, TN, and TP. The results indicated that the accuracy of all models increased when GA was applied to neural networks. The mean average error for the hybrid models varied from 3 to 8%.

Performance evaluation and modelling of an integrated municipal wastewater treatment system using neural networks

“…Figure 6 demonstrates that the MLP-NN model predicted the effluent COD, TP, and TSS with high accuracy based on the test data set. The results of our study confirm a high generalisation capability of MLP-NN algorithm, as has been reported in a number of studies (Bagheri et al, 2015;2016b;Mirbagheri et al, 2015). Figure 7 demonstrates the regression lines for the MLP-NN model predicting effluent COD, TP, and TSS based on the train, test, validation, and all data sets.…”

“…Artificial intelligence and machine learning techniques have shown high capabilities in various fields of science and engineering (Kavousi and Saadatmand, 2018). Neural networks (NNs) are artificial intelligent models, which have been successfully used for monitoring and predicting various parameters in water and wastewater treatment (Mirbagheri et al, 2015; Bagheri et al, 2016a; 2016b). In recent years, the NNs have been frequently used due to their several advantages over activated sludge models such as parameter estimation and calibration (Bagheri et al, 2019).…”

Water Reuse Planning for Fulfilment of Clean Water in Indonesia

“…It makes and gives some options for the water reuse process that can be installed and built as needed from the cases. Membrane bioreactors (MBR) is defined as a mechanical system that consists from some any part such as backwash pumps, effluent pumps, timer, pressure gauges, membrane modules, feeding tanks, and some the others [14]. Basically this mechanism was doing some filtration from any molecules or particle that needed to clean up and make the water in better quality.…”

Exploring Nanosilver-Coated Hollow Fiber Microfiltration to Mitigate Biofouling for High Loading Membrane Bioreactor

“…Since Yamamoto and his colleague proposed the idea of submerging membranes in the bioreactor in 1989, the membrane bioreactor (MBR) has become a technology that competes with conventional activated sludge process. This process has several advantages, such as high organic loading rate, due to the high mix liquor suspended solid concentration (MLSS) in the bioreactor, lower excess sludge production caused by higher sludge retention time (SRT), lower physical footprint owing to shorter hydraulic retention time (HRT), and excellent effluent water quality [1,2,3]. In spite of its reputation as a secure and high operational reliability technology, membrane fouling is still a major problem that hinders the widespread and large-scale applications [4].…”