Biomedical subjects

M Sànchez-Marrè

Publications and source records attributed to M Sànchez-Marrè.

4 recordsLinked to original sources

PubMed2006

Case-based reasoning, a promising tool to face solids separation problems in the activated sludge process.

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.

Decision Support Techniques↗

PubMed2003

A knowledge-based approach to the deflocculation problem: integrating on-line, off-line, and heuristic information.

A knowledge-based approach for the supervision of the deflocculation problem in activated sludge processes was considered and successfully applied to a full-scale plant. To do that, a methodology that integrates on-line, off-line and heuristic information has been proposed. This methodology consists of three steps: (i). development of a decision tree (which involves knowledge acquisition and representation); (ii). implementation into a rule-based system; and (iii). validation. The set of symptoms most useful in diagnosing the deflocculation problem has been identified, the different branches to diagnose pin-point floc and dispersed growth have been built (using generic and specific knowledge), and all this knowledge has been codified into an object-oriented shell. The results obtained in the application of this knowledge-based approach to the Granollers WWTP (which treats about 130000 inhabitants-equivalents) showed that the system was able to identify correctly the problem with reasonable accuracy. Our positive experience building this system suggests that this approach is a practical and valuable element to include in an intelligent supervisory system combining numerical and reasoning techniques.

Artificial Intelligence↗

PubMed2002

A hybrid supervisory system to support WWTP operation: implementation and validation.

Integrated operation of Wastewater Treatment Plants is still far from being solved. A reasonable proposal should link advanced and robust control algorithms to some knowledge-based techniques, allocating the detailed engineering to numerical computations, while delegating the logical analysis and reasoning to supervisory intelligent systems. This paper describes the development and implementation of a knowledge-based Hybrid Supervisory System to support the operation of a real Wastewater Treatment Plant. The system integrates different reasoning modules, overcoming the limitations in the use of each single technique, while providing an agent based architecture with additional modularity and independence. It is structured into three separated levels: data gathering, diagnosis, and decision support. The different tasks of the system are performed in a seven-step cycle: data gathering and update, diagnosis, supervision, prediction, communication, actuation, and evaluation phase. In spite of certain reservations of the scientific community about the use of these techniques, the system is successfully performing real-time support to the operation of the Granollers facility since September 1999. Results of the first four-month validation period are shown and discussed. An example of the system behavior is also shown in the paper. The conclusions indicate the key steps which are necessary to transfer the system to another facility.

Algorithms↗

PubMed2001

Development of a case-based system for the supervision of an activated sludge process.

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.

Bacteria↗