Based on the developed neural-fuzzy control system for anaerobic hybrid reactor （AHR） in wastewater treatment and biogas production, the neural network with backpropagation algorithm for prediction of the variables ...Based on the developed neural-fuzzy control system for anaerobic hybrid reactor （AHR） in wastewater treatment and biogas production, the neural network with backpropagation algorithm for prediction of the variables pH, alkalinity （Alk） and total volatile acids （TVA） at present day time t was used as input data for the fuzzy logic to calculate the influent feed flow rate that was applied to control and monitor the process response at different operations in the initial, overload influent feeding and the recovery phases. In all three phases, this neural-fuzzy control system showed great potential to control AHR in high stability and performance and quick response. Although in the overloading operation phase II with two fold calculating influent flow rate together with a two fold organic loading rate （OLR）, this control system had rapid response and was sensitive to the intended overload. When the influent feeding rate was followed by the calculation of control system in the initial operation phase I and the recovery operation phase III, it was found that the neural-fuzzy control system application was capable of controlling the AHR in a good manner with the pH close to 7, TVA/Alk 〈 0.4 and COD removal 〉 80% with biogas and methane yields at 0.45 and 0.30 m^3/kg COD removed.展开更多
基金the Thailand Graduate Institute of Science and Technology(No. TGIST 01-47-038)the National Science and Technology Development Agency(NSTDA) for Ph.D.Scholarship to Mr. Chaiwat Waewsakthe National Research Council of Thailand for research grant under Fiscal Year 2008 Budget to King Mongkut’s University of Technology Thonburi
文摘Based on the developed neural-fuzzy control system for anaerobic hybrid reactor （AHR） in wastewater treatment and biogas production, the neural network with backpropagation algorithm for prediction of the variables pH, alkalinity （Alk） and total volatile acids （TVA） at present day time t was used as input data for the fuzzy logic to calculate the influent feed flow rate that was applied to control and monitor the process response at different operations in the initial, overload influent feeding and the recovery phases. In all three phases, this neural-fuzzy control system showed great potential to control AHR in high stability and performance and quick response. Although in the overloading operation phase II with two fold calculating influent flow rate together with a two fold organic loading rate （OLR）, this control system had rapid response and was sensitive to the intended overload. When the influent feeding rate was followed by the calculation of control system in the initial operation phase I and the recovery operation phase III, it was found that the neural-fuzzy control system application was capable of controlling the AHR in a good manner with the pH close to 7, TVA/Alk 〈 0.4 and COD removal 〉 80% with biogas and methane yields at 0.45 and 0.30 m^3/kg COD removed.
