APPLICATION OF COMPUTATIONAL INTELLIGENCE FOR ONLINE CONTROL OF A SEQUENCING BATCH REACTOR (SBR) AT MORRINSVILLE SEWAGE-TREATMENT PLANT

Morrinsville Sewage Treatment Plant has recently been upgraded to an E xtended Aeration SBR. The plant needs to comply with stringent dischar ge requirements despite the variations in organic and hydraulic load c aused by tradewaste discharges and stormwater infiltration. Effluent d ata from a nearby dairy factory is transmitted to the treatment plant by radio and processed by a back propagation neural network trained to correlate the data with the corresponding BOD. BOD oxidation, nitrifi cation acid denitrification rate constants are estimated by fuzzy syst ems as function of temperature and MLVSS. Output data generated by the model are used to assist control of SDR cycle duration, sludge wastin g, and temporary storage of excessive load in a lagoon. The model does not pretend to provide an accurate description of the process, nor a fully optimised control system, bur rather a common-sense approach to the very challenging operating conditions. This is a plant receiving a low level of supervision and it is expected that the control system w ill improve process performance and compliance with discharge requirem ents. (C) 1997 IAWQ. Published by Elsevier Science Ltd.