Classical control has serious limitations when faced with solids separation problems in the activated sludge process. Lack of knowledge about the mechanisms involved in the imbalance within the different microbiological communities implies that a general solution to these undesirable situations has not yet been provided. However, operators have to make decisions based on their experience and intuition to solve the problem (or at least to minimise the effects). The acquisition and registration of the knowledge learnt from each new experience can be decisive when solving similar problems in the future. Case-based reasoning (CBR) is an advanced technique for knowledge management in complex systems that uses past experiences to solve brand new situations. Previous simplified proposals in this field have exposed limitations, but this paper describes a new approach to CBR, considering the dynamics and the complexity of solids separation problems.

This content is only available as a PDF.