CONCEPT-FORMATION IN WWTP BY MEANS OF CLASSIFICATION TECHNIQUES - A COMPARED STUDY

Although activated sludge process is a very widely used biological pro cess in wastewater treatment plants (WWTP), and there are properly fun ctioning control loops such as that of dissolved oxygen, in practice, this type of plant requires a major time investment on the part of the operator, involving many manual operations. Treatment plants work wel l most of the time, as long as there are not unforeseen occurrences. N ormal operating situations (generally similar to design conditions) ca n be treated mathematically by using efficient control algorithms. How ever, there are situations in which the control system cannot properly manage the plant, and in which the process can only be efficiently ma naged thanks to the operator's experience. This is a case in which a k nowledge-based system may be useful. One of the difficulties inherent to the development of a knowledge-based system is to obtain the knowle dge base (i.e., knowledge acquisition), specially when dealing with a wide, complicated and ill-structured field. Among the aims of this wor k are those to show how semi-automatic knowledge acquisition tools cou ld help human experts to organize their knowledge about their domain a nd also, to compare the power of different approaches of knowledge acq uisition to the same database. In this paper are presented the results obtained from applying two different classification techniques to the development of knowledge-bases for the management of an activated slu dge process.