Effects of phase vector and history extension on prediction power of adaptive-network based fuzzy inference system (ANFIS) model for a real scale anaerobic wastewater treatment plant operating under unsteady state |
| |
Authors: | Altınay Perendeci Sever Arslan Abdurrahman Tanyolaç Serdar S Çelebi |
| |
Institution: | 1. Environmental Engineering Department, Akdeniz University, 07058 Antalya, Turkey;2. Turkish Sugar Factories Corporation, Electromechanic Instruments Factory, Etimesgut, 06790 Ankara, Turkey;3. Chemical Engineering Department, Hacettepe University, Beytepe, 06800 Ankara, Turkey |
| |
Abstract: | A conceptual neural fuzzy model based on adaptive-network based fuzzy inference system, ANFIS, was proposed using available input on-line and off-line operational variables for a sugar factory anaerobic wastewater treatment plant operating under unsteady state to estimate the effluent chemical oxygen demand, COD. The predictive power of the developed model was improved as a new approach by adding the phase vector and the recent values of COD up to 5–10 days, longer than overall retention time of wastewater in the system. History of last 10 days for COD effluent with two-valued phase vector in the input variable matrix including all parameters had more predictive power. History of 7 days with two-valued phase vector in the matrix comprised of only on-line variables yielded fairly well estimations. The developed ANFIS model with phase vector and history extension has been able to adequately represent the behavior of the treatment system. |
| |
Keywords: | Anaerobic wastewater treatment Adaptive-network based fuzzy inference system History extension Modeling Phase vector |
本文献已被 ScienceDirect 等数据库收录! |
|