Hybrid artificial neural network genetic algorithm technique for modeling chemical oxygen demand removal in anoxic/oxic process

In this paper, a hybrid artificial neural network (ANN) - genetic algorithm (GA) numerical technique was successfully developed to deal with complicated problems that cannot be solved by conventional solutions. ANNs and Gas were used to model and simulate the process of removing chemical oxygen demand (COD) in an anoxic/oxic system. The minimization of the error function with respect to the network parameters (weights and biases) has been considered as training of the network. Real-coded genetic algorithm was used to train the network in an unsupervised manner. Meanwhile the important process parameters, such as the influent COD (CODin), reflux ratio (R r ), carbon-nitrogen ratio (C/N) and the effluent COD (CODout) were considered. The result shows that compared with the performance of ANN model, the performance of the GA-ANN (genetic algorithm - artificial neural network) network was found to be more impressive. Using ANN, the mean absolute percentage error (MAPE), mean squared error (MSE) and correlation coefficient (R) were 9.33×10−4, 2.82 and 0.98596, respectively; while for the GA-ANN, they were converged to be 4.18×10−4, 1.12 and 0.99476, respectively.

[1]  Bryn V. Williams.  Evolutionary neural networks : models and applications , 1995 .

[2]  James C. Spall,et al.  A neural network controller for systems with unmodeled dynamics with applications to wastewater treatment , 1997, IEEE Trans. Syst. Man Cybern. Part B.

[3]  J. M. Park,et al.  Neural network modeling for on-line estimation of nutrient dynamics in a sequentially-operated batch reactor. , 1999, Journal of biotechnology.

[4]  Peter A Vanrolleghem,et al.  Parallel hybrid modeling methods for a full-scale cokes wastewater treatment plant. , 2005, Journal of biotechnology.

[5]  David M. Skapura,et al.  Neural networks - algorithms, applications, and programming techniques , 1991, Computation and neural systems series.

[6]  Krist V. Gernaey,et al.  Activated sludge wastewater treatment plant modelling and simulation: state of the art , 2004, Environ. Model. Softw..

[7]  Wen K. Shieh,et al.  OPTIMAL CONTROL OF WASTEWATER TREATMENT PLANTS VIA INTEGRATED NEURAL NETWORK AND GENETIC ALGORITHMS , 2001 .

[8]  Farouq S Mjalli,et al.  Use of artificial neural network black-box modeling for the prediction of wastewater treatment plants performance. , 2007, Journal of environmental management.

[9]  Ni-Bin Chang,et al.  Rough set-based hybrid fuzzy-neural controller design for industrial wastewater treatment. , 2003, Water research.

[10]  James M. Hamlett,et al.  Watershed optimization of best management practices using AnnAGNPS and a genetic algorithm , 2002 .

[11]  L. Belanchea,et al.  Prediction of the bulking phenomenon in wastewater treatment plants , 2000 .

[12]  Davut Hanbay,et al.  Prediction of wastewater treatment plant performance based on wavelet packet decomposition and neural networks , 2008, Expert Syst. Appl..

[13]  Iván Machón,et al.  Simulation of a coke wastewater nitrification process using a feed-forward neuronal net , 2007, Environ. Model. Softw..

[14]  Ni-Bin Chang,et al.  Fuzzy controller design for municipal incinerators with the aid of genetic algorithms and genetic programming techniques , 2000 .

[15]  Robert Tenno,et al.  State and parameter estimation for wastewater treatment processes using a stochastic model , 1995 .

[16]  Wang Yan,et al.  Control rules of aeration in a submerged biofilm wastewater treatment process using fuzzy neural networks , 2009, Expert Syst. Appl..

[17]  Lluís A. Belanche Muñoz,et al.  Prediction of the bulking phenomenon in wastewater treatment plants , 2000, Artif. Intell. Eng..

[18]  H. Ishibuchi,et al.  Selecting fuzzy rules by genetic algorithm for classification problems , 1993, [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems.