Treating Simulative Domestic Wastewater Using SBBR-CRI Process And Its Simulation Study Based On Artificial Neural Network

With the development of the economy, China is facing the problem of water pollution and water shortage. Attention is paid to sewage treatment, especially the decentralized sewage treatment. The decentralized sewage had become a problem because of the change of water quantity and quality and little water. Researchers have been devoting themselves to develop low cost, small installation footprint and simple operation and maintenance new treatment. In this paper, current situation of water resource and the problem of water resource were introduced. At the same time, water contamination in recent years and this brings harm to people’s daily life were introduced. The paper also introduces the recent domestic sewage treatments and its application. Through compare the advantages and disadvantages of sewage treatment, the water technology of SBBR combined with CRI was employed to treat simulative domestic wastewater.Three reactors were used to treat simulative domestic wastewater and comparing the removal efficiency of COD, NH₄⁺-N、TN and TP of SBBR and CRI respectively, and in contrast with the removal efficiency of SBBR-CRI. Through the single element experiment, the optimal condition of the parameters was obtained. SBBR-CRI process was simulated using the artificial neural network which adapted to the complicated nonlinear relation between the influence factors and the effluent parameters. The artificial neural network with adaptive study algorithm was built with the inputs of DO, wetting time/drying time, aeration time/nonaeration time, the influent COD, NH₄⁺-N, TP and outputs of the effluent COD, NH₄⁺-N,TN, TP using MATLAB software. Combining with the parameter optimization of SI 6, lr 0.13, mc 0.6, studying time 6000, the numerical outputs and the experimental values matched well, and the MARE of the sample were within 7.5% and the RSM were within 0.085. The results indicated that NH₄⁺-N removal efficiency was over 98%, TN and TP removal efficiency were both over 85% and COD removal efficiency was over 94% under the conditions of DO concentration 2mg/L, aeration time/nonaeration time 2/1 and wetting time/drying time 1/3.The value contribution relationships between each input factor and output results were studied by weighted average analysis, which indicated that the influent DO, NH₄⁺-N and TP had a strong impact on the effluent parameters. In the effluent parameters, the effluent TN was influenced most by wet/dry（w/d） ratio of the constructed rapid infiltration. The ANN which has the nonlinear approximation ability identify the relation between input and output by the nonlinear mapping relation, that provides the condition for the online monitoring.