Stochastic modeling applications for the prediction of COD removal efficiency of UASB reactors treating diluted real cotton textile wastewater

Abstract

A three-layer Artificial Neural Network (ANN) model (9:12:1) for the prediction of Chemical Oxygen Demand Removal Efficiency (CODRE) of Upflow Anaerobic Sludge Blanket (UASB) reactors treating real cotton textile wastewater diluted with domestic wastewater was presented. To validate the proposed method, an experimental study was carried out in three lab-scale UASB reactors to investigate the treatment efficiency on total COD reduction. The reactors were operated for 80 days at mesophilic conditions (36-37.5°C) in a temperature-controlled water bath with two hydraulic retention times (HRT) of 4.5 and 9.0 days and with organic loading rates (OLR) between 0.072 and 0.602 kg COD/m 3 /day. Five different dilution ratios of 15, 30, 40, 45 and 60% with domestic wastewater were employed to represent seasonal fluctuations, respectively. The study was undertaken in a pH range of 6.20-8.06 and an alkalinity range of 1,350-1,855 mg/l CaCO 3 . The concentrations of volatile fatty acids (VFA) and total suspended solids (TSS) were observed between 420 and 720 mg/l CH 3 COOH and 68-338 mg/l, respectively. In the study, a wide range of influent COD concentrations (COD i ) between 651 and 4,044 mg/l in feeding was carried out. CODRE of UASB reactors being output parameter of the conducted anaerobic treatment was estimated by nine input parameters such as HRT, pH, COD i concentration, operating temperature, alkalinity, VFA concentration, dilution ratio (DR), OLR, and TSS concentration. After backpropagation (BP) training combined with principal component analysis (PCA), the ANN model predicted CODRE values based on experimental data and all the predictions were proven to be satisfactory with a correlation coefficient of about 0.8245. In the ANN study, the Levenberg-Marquardt Algorithm (LMA) was found as the best of 11 BP algorithms. In addition to determination of the optimal ANN structure, a linear-nonlinear study was also employed to investigate the effects of input variables on CODRE values in this study. Both ANN outputs and linear-nonlinear study results were compared and advantages and further developments were evaluated.

A Prognostic Approach Based on Fuzzy-Logic Methodology to Forecast PM10 Levels in Khaldiya Residential Area, Kuwait

“…For comparative purpose, the measured data were evaluated by a multiple regression software package (DataFit® V8.1.69, Copyright© 1995, Oakdale Engineering, PA, RC167), containing 298 two-dimensional (2D) and 242 three-dimensional (3D) non-linear regression models. The regression analysis was performed based on the Levenberg-Marquardt method with double precision, as similarly done in several studies of the first author (Yetilmezsoy, 2007;Yetilmezsoy and Saral, 2007;Yetilmezsoy and Sapci-Zengin, 2009;Yetilmezsoy and Sakar, 2008;Turkdogan-Aydinol and Yetilmezsoy, 2010;Yetilmezsoy, 2011;Yetilmezsoy, 2012).…”

“…Although statistical models may be able to establish a relationship between the input and the output variables without detailing the causes and effects in the formation of pollutants, however, they are not capable of capturing the inherent non-linear nature of the problem and forecasting short-term pollution levels (Agirre-Basurko et al, 2006;Barai et al, 2007;Akkoyunlu et al, 2010). Since the number of meteorological and pollution parameters implies highdimensional input space and high computational capacity, it is believed that artificial intelligence-based techniques may provide a good alternative to traditional techniques due to their speed, robustness and non-linear characteristics (Yetilmezsoy and Sapci-Zengin, 2009;Akkoyunlu et al, 2010).…”

Modelling Biogas Fermentation from Anaerobic Digestion: Potato Starch Processing Wastewater Treated Within an Up flow Anaerobic Sludge Blanket

“…Deterministic models also provide a good insight into the mechanism of biological relationships, but fluctuation of kinetic parameters and wastewater characteristics normally results in a laborious calibration, comprehensive computer analysis as well as laboratory work [14]. The International Water Association (IWA) Anaerobic Digestion Model No.1 (ADM1), a typical deterministic model, has been successfully used for modeling the whole anaerobic digestion process [19].…”

“…Other reports also confirmed that process modeling based on previously acquired data is one technical route to enhancing the performance of anaerobic processes. These process models are often developed [14,15]. Nonetheless, modeling of anaerobic digestion is quite challenging and tough because performance of anaerobic systems is complex and varies considerably with influent characteristics and operational conditions [16].…”

MSG Wastewater Treatment with UASB-AOMBR Coupling process

“…The substrate composition and organic loading rate on the process performance during start-up and steady state were studied by N. Musee (2007) [6] , Kaan Yetilmezsoy (2009) [7] Matsumoto and Noike (1991) [8] . The optimum values of operating variables for treating hog wastewater were reported (Chen et al, 1997) [9] for the anaerobic fluidized bed treatment of hog wastewater. The feasibility of treatment of monosodium glutamate fermentation wastewater was evaluated (Tseng and Lin, 1990) [10] in terms of removal efficiency and methane content in the biogas.…”