DAI-DEPUR - AN INTEGRATED AND DISTRIBUTED ARCHITECTURE FOR WASTE-WATER TREATMENT PLANTS SUPERVISION

The activated sludge process - the main biological technology usually applied to wastewater treatment plants (WWTP) - directly depends on li ve beings (microorganisms), and therefore on unforeseen changes produc ed by them. It could be possible to get a good plant operation if the supervisory control system is able to react to the changes and deviati ons in the system and can take the necessary actions to restore the sy stem's performance. These decisions are often based both on physical, chemical, microbiological principles (suitable to be modelled by conve ntional control algorithms) and on some knowledge (suitable to be mode lled by knowledge-based systems). But one of the key problems in knowl edge-based control systems design is the development of an architectur e able to manage efficiently the different elements of the process (in tegrated architecture), to learn from previous cases (specific experim ental knowledge) and to acquire the domain knowledge (general expert k nowledge). These problems increase when the process belongs to an ill- structured domain and is composed of several complex operational units . Therefore, an integrated and distributed AI architecture seems to be a good choice. This paper proposes an integrated and distributed supe rvisory multi-level architecture for the supervision of WWTP, that ove rcomes some of the main troubles of classical control techniques and t hose of knowledge-based systems applied to real world systems.