Comparison of chemical-biological flocculation process model based on artificial neural network
Based on the experimental research on a pilot units of the chemical-biological flocculation process, the multi-input multi-output (MIMO) model and the multi-input single-output (MISO) model have been built followed by the back-propagation (BP) artificial networks. Trained by the data (water temperatures, flocculant dosages, recycle ratio, CODCr, TP, SS, etc.) from the six different operating modes of the processes, all of the two models achieved convergence well. The data of another two operating modes was used for the model prediction. The relative errors of the MISO model prediction were lower than those of the MIMO model prediction; and all of relative errors from the MISO model prediction were less than 9.0％. As a result, the MISO model is an easy-to-use modelling tool to obtain a quick preliminary assessment for the effluent quality prediction of the chemical-biological flocculation process.
chemical-biological flocculation artificial neural network MIMO MISO
Huang Tian-yin Li Ning Xia Si-qing Huang Yong
School of Environmental Science and Engineering Suzhou University of Science and Technology Suzhou, School of the Environment Jiangsu University Zhenjiang, China State Key Laboratory of Pollution Control and Resources Reuse Tongji University Shanghai, China
国际会议
上海
英文
824-827
2008-05-16（万方平台首次上网日期，不代表论文的发表时间）