Modeling and optimization of activated sludge bulking for a real wastewater treatment plant using hybrid artificial neural networks-genetic algorithm approach

2015 ◽  
Vol 95 ◽  
pp. 12-25 ◽  
Author(s):  
Majid Bagheri ◽  
Sayed Ahmad Mirbagheri ◽  
Zahra Bagheri ◽  
Ali Morad Kamarkhani
Keyword(s):  
Genetic Algorithm ◽  
Neural Networks ◽  
Wastewater Treatment ◽  
Artificial Neural Networks ◽  
Activated Sludge ◽  
Wastewater Treatment Plant ◽  
Treatment Plant ◽  
Modeling And Optimization ◽  
Genetic Algorithm Approach ◽  
Real Wastewater

Integrated Wastewater Treatment Plant Performance Evaluation Using Artificial Neural Networks

1999 ◽  
Vol 40 (7) ◽  
pp. 55-65 ◽  
Author(s):  
Mohamed F. Hamoda ◽  
Ibrahim A. Al-Ghusain ◽  
Ahmed H. Hassan
Keyword(s):  
Neural Networks ◽  
Wastewater Treatment ◽  
Artificial Neural Networks ◽  
Wastewater Treatment Plant ◽  
Municipal Wastewater ◽  
Wastewater Treatment Plants ◽  
Treatment Plant ◽  
Plant Performance ◽  
Municipal Wastewater Treatment ◽  
Artificial Neural

Proper operation of municipal wastewater treatment plants is important in producing an effluent which meets quality requirements of regulatory agencies and in minimizing detrimental effects on the environment. This paper examined plant dynamics and modeling techniques with emphasis placed on the digital computing technology of Artificial Neural Networks (ANN). A backpropagation model was developed to model the municipal wastewater treatment plant at Ardiya, Kuwait City, Kuwait. Results obtained prove that Neural Networks present a versatile tool in modeling full-scale operational wastewater treatment plants and provide an alternative methodology for predicting the performance of treatment plants. The overall suspended solids (TSS) and organic pollutants (BOD) removal efficiencies achieved at Ardiya plant over a period of 16 months were 94.6 and 97.3 percent, respectively. Plant performance was adequately predicted using the backpropagation ANN model. The correlation coefficients between the predicted and actual effluent data using the best model was 0.72 for TSS compared to 0.74 for BOD. The best ANN structure does not necessarily mean the most number of hidden layers.

Genetic algorithms for the application of Activated Sludge Model No. 1

2002 ◽  
Vol 45 (4-5) ◽  
pp. 405-411 ◽  
Author(s):  
S. Kim ◽  
H. Lee ◽  
J. Kim ◽  
C. Kim ◽  
J. Ko ◽  
...  
Keyword(s):  
Wastewater Treatment ◽  
Activated Sludge ◽  
Wastewater Treatment Plant ◽  
Treatment Plant ◽  
Global Optimum ◽  
Data Sets ◽  
Local Optima ◽  
Real Wastewater ◽  
The Difference ◽  
Substrate Concentrations

The genetic algorithm (GA) has been integrated into the IWA ASM No.1 to calibrate important stoichiometric and kinetic parameters. The evolutionary feature of GA was used to configure the multiple local optima as well as the global optimum. The objective function of optimization was designed to minimize the difference between estimated and measured effluent concentrations at the activated sludge system. Both steady state and dynamic data of the simulation benchmark were used for calibration using denitrification layout. Depending upon the confidence intervals and objective functions, the proposed method provided distributions of parameter space. Field data have been collected and applied to validate calibration capacity of GA. Dynamic calibration was suggested to capture periodic variations of inflow concentrations. Also, in order to verify this proposed method in real wastewater treatment plant, measured data sets for substrate concentrations were obtained from Haeundae wastewater treatment plant and used to estimate parameters in the dynamic system. The simulation results with calibrated parameters matched well with the observed concentrations of effluent COD.

Sign in / Sign up

Export Citation Format

Share Document