Wastewater treatment improvement through an intelligent integrated supervisory system

Aquest article mostra el resultat de la col·laboracio portada a terme durant els darrers anys entre grups d'enginyeria quimica, enginyeria ambiental i intel·ligencia artificial. El treball se centra en el desenvolupament de tecniques per a la millora i supervisio de processos complexos, especialment del tractament biologic d'aigues residuals. L'experiencia demostra que la millor opcio requereix desenvolupar un sistema supervisor que combini i integri tecniques de control classic (controlador automatic del nivell d'oxigen dissolt en el reactor biologic, us de models descriptius del proces, etc.) amb sistemes basats en el coneixement (concretament sistemes experts i sistemes basats en casos). El present article descriu la complexitat de la gestio del proces de tractament de les aigues residuals, l'arquitectura integrada que es proposa i el desenvolupament i la construccio de cadascun dels moduls d'aquesta proposta per a la implementacio real a l'estacio depuradora d'aigues residuals de Granollers. Finalment, es detallen alguns resultats del proces de validacio del seu funcionament enfront de situacions quotidianes de la planta.

[1]  Miquel Sànchez-Marrè,et al.  DAI-DEPUR: an integrated and distributed architecture for wastewater treatment plants supervision , 1996, Artif. Intell. Eng..

[2]  M. Poch,et al.  Automatic Knowledge Acquisition from Complex Processes for the Development of Knowledge-Based Systems , 2001 .

[3]  James K. Lein.  Environmental decision making : an information technology approach , 1997 .

[4]  Miquel Sànchez-Marrè,et al.  Sustainable case learning for continuos domains , 1999, Environ. Model. Softw..

[5]  Ulises Cortés,et al.  ISCWAP : A knowledge-based system for supervising activated sludge processes , 1997 .

[6]  Joaquim Comas,et al.  Thesis: Development, Implementation and Evaluation of an Activated Sludge Supervisory System for the Granollers WWTP , 2001, AI Commun..

[7]  Miquel Sànchez-Marrè,et al.  Learning and Adaptation in Wastewater Treatment Plants Through Case–Based Reasoning , 1997 .

[8]  J Comas,et al.  Development of a Case-Based System for the Supervision of an Activated Sludge Process , 2001, Environmental technology.

[9]  Lluís A. Belanche Muñoz,et al.  Towards a model of input-output behaviour os wastewater treatment plants using soft computing techniques , 1999, Environ. Model. Softw..

[10]  C. S. Fu,et al.  Application of a multi-layered neural network to system identification , 1993 .

[11]  S. A. Manesis,et al.  Intelligent control of wastewater treatment plants , 1998, Artif. Intell. Eng..

[12]  Lluís A. Belanche Muñoz,et al.  Prediction of the bulking phenomenon in wastewater treatment plants , 2000, Artif. Intell. Eng..

[13]  Chunsheng Fu,et al.  Fuzzy modeling and pattern recognition for dynamic processes and its application for an activated sludge process , 1995 .

[14]  Mogens Henze,et al.  Wastewater Treatment: Biological and Chemical Processes , 1995 .

[15]  Janet L. Kolodner,et al.  Case-Based Reasoning , 1989, IJCAI 1989.

[16]  Miquel Sànchez-Marrè,et al.  Knowledge discovery by means of inductive methods in wastewater treatment plannt data , 2001, AI Commun..

[17]  W. Gujer,et al.  Activated sludge model No. 3 , 1995 .

[18]  Chunsheng Fu,et al.  System identification and real-time pattern recognition by neural networks for an activated sludge process , 1995 .

[19]  A. Brennan.  Environmental Decision-Making , 1993 .

[20]  Manel Poch,et al.  Fuzzy model and decision of COD control for an activated sludge process , 1998, Fuzzy Sets Syst..