Development of a Case-Based System for the Supervision of an Activated Sludge Process

• Published in: Environmental technology Vol. 22; no. 4; pp. 477 - 486
• Main Authors: Roda, I. R., Sànchez-Marrè, M., Comas, J., Cortes, U., Poch, M.
• Format: Journal Article
• Language: English
• Published: London Taylor & Francis Group 01.04.2001; Selper
• Subjects: activated sludge; Applied sciences; Bacteria; Biological and medical sciences; Biological treatment of waters; Biotechnology; Case-based reasoning; control; Decision Making; Environment and pollution; Exact sciences and technology; Fundamental and applied biological sciences. Psychology; General purification processes; Humans; Industrial applications and implications. Economical aspects; Knowledge; Pollution; Sanitary Engineering - methods; Sewage - chemistry; Spain, Girona; supervision; Waste Disposal, Fluid - methods; wastewater; Wastewaters; Water treatment and pollution; Europe; Spain; Activated sludge; Supervision architecture; Process control; Expert system; Case based reasoning; Waste water purification; Intelligent system; Biological purification
• ISSN: 0959-3330; 1479-487X
• DOI: 10.1080/09593332208618277

The development of a case-based reasoning system for the supervision of an activated sludge process is presented here. The methodology proposed permits the use of past experiences to solve new problems that arise in the process. These experiences are classified as cases or situations. The adaptation of cases and the generation of new cases are used to tune the response of the system and to learn from the new information generated by the process. The case and the case library definition, the initial seed, the search and retrieval process, the adaptation, the action, the evaluation and the learning steps are presented and outlined. The process studied is the wastewater treatment plant of Girona, Spain. Two examples of the response of the system to two different operational situations are presented. The paper also outlines the integration of different fields in a multidisciplinary approach as the most optimal solution to ensure the successful control and supervision of complex processes like the activated sludge process. With this aim the integration of an array of specific supervisory intelligent systems (for the logical analysis and reasoning) and numerical computations for detailed engineering is suggested.