Development of a real-time control strategy with artificial neural networkfor automatic control of a continuous-flow sequencing batch reactor

The purpose of this study is to develop a reliable and effective real-time control strategy by integrating artificial neural network (ANN) process mod els to perform automatic operation of a dynamic continuous-flow SBR system. The ANN process models, including ORP/pH simulation models and water quali ty ([NH4+-N] and [NOx--N]) prediction models, can assist in real-time searc hing the ORP and pH control points and evaluating the operation performance s of aerobic nitrification and anoxic denitrification operation phases. Sin ce the major biological nitrogen removal mechanisms were controlled at nitr itification (NH4+- N --> NO2--N) and clenitritification (NO2--N -->N-2) sta ges, as well as the phosphorus uptake and release could be completely contr olled during aerobic and anoxic operation phases, the system operation perf ormances under this ANN real-time control system revealed that both the aer ation time and overall hydraulic retention time could be shortened to about 1.9-2.5 and 4.8-6.2 hrs/cycle respectively. The removal efficiencies of CO D, ammonia nitrogen, total nitrogen, and phosphate were 98%, 98%, 97%, and 84% respectively, which were more effective and efficient than under conven tional fixed-time control approach.