Knowledge-based techniques in wastewater treatment plants managment

Authors

Miquel Sànchez-Marrè miquel@lsi.upc.es
Ulises Cortés ia@lsi.upc.es

Departament de Llenguatges i Sistemes Informàtics
Universitat Politècnica de Catalunya
Edifici C5-Campus Nord
C/ Jordi Girona 1-3
08034 Barcelona, Catalonia, Spain

Javier Lafuente lafuente@uab-eq.uab.es

Departament d'Enginyeria Química
Universitat Autònoma de Barcelona
Edifici C
08193 Bellaterra (Barcelona), Catalonia, Spain

Ignasi R-Roda eqairr@fc.udg.es
Manel Poch eqampe@fc.udg.es

Laboratori d'Enginyeria Química i Ambiental.
Facultat de Ciències
Universitat de Girona
Campus de Montilivi
17071 Girona, Catalonia, Spain

Abstract

This article, presents the main knowledge-based techniques of Artificial Intelligence used for wastewater treatment plants (WWTP) management, and also, points to some real applications. First, a survey of WWTP describes the complexity of the system being modelled and outlines its difficulties. The activated sludge process the main biological technology usually applied to WWTP directly depends on live beings (microorganisms), and therefore, on changes experimented 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 deviations of the system and can take the necessary actions 3 to restore the system's performance. These decisions are often based both in Physical, Chemical, Microbiological principles (suitable to be modelled by conventional control algorithms) and in the experience acquired from similar situations, previously detected and solved (not included in such classical control models). So, these features reveal that supervision and control of activated sludge processes, could only be treated in a multi-disciplinary way, that includes: monitoring (sensor developing, continuous analysis equipment, real time), modelling (equations that model the bioreactors' behaviour), control (maintaining good effluent water quality and reducing operation costs), qualitative information (microbiological information, water colour and odour, water appearance, etc.) and expert knowledge (supplied by the large experience from plants' managers, biologists and operators). Both last features, commonly provide the systems with incomplete, uncertain or approximate information. Afterwards, some basic ideas about Automatic Process Control, Artificial Intelligence and Real Time Systems are exposed. Next sections describe the most usual knowledge-based AI techniques applied to WWTP, as well as several applications: Decision-aided systems, Expert systems, Knowledge-based systems and Distributed intelligent systems. Finally, an example of a real application's architecture is detailed (DAI-DEPUR).

Keywords: Expert systems, Knowledge-based systems, Intelligent decision support systems, Expert control systems, Distributed intelligent systems, Distributed Artificial Intelligence, Artificial Intelligence, Wastewater treatment, Wastewater treatment management, Wastewater treatment applications, Chemical Engineering, Environmental Engineering.

Citation

M. SÓnchez, U. CortÚs, J. Lafuente, I. R.-Roda, and M. Poch, "Knowledge-based techniques in wastewater treatment plants managment". Submitted to Enciclopedia of Life Support Systems (EOLSS). September, 1995.

Postscript

You may want a postcript version of the article: "Knowledge-based techniques in wastewater treatment plants managment"


Back to the Artifical Intelligence Section page


Last modified on .

Page mantainer: webia@lsi.upc.es