Initial Sensor Network Design with A Multi-Objective Genetic Algorithm

CARBALLIDO JESSICA A.; PONZONI IGNACIO; BRIGNOLE NÉLIDA B.

Buenos Aires, Argentina

Simposio; ASAI 2003 (Argentine Symposium on Artificial Intelligence, XXXII Jornadas Argentinas de Informática e Investigación Operativa); 2003

Sociedad Argentina de Informática e Investigación Operativa

A Multi-Objective Genetic Algorithm (MOGA) application, which is based on the aggregating approach, is proposed in this article. Its aim is to find a consistent instrument configuration for industrial process plants that will constitute a convenient initial set of input data for structural Observability Analysis Algorithms (OAs). The better this configuration is, the faster the OAs will converge to a satisfactory solution. Algorithmic effectiveness was evaluated through the analysis of small academic case studies. The results obtained through our algorithm show excellent performance. Therefore, it can be stated that the prototype presented in this work is good enough to serve as a sound basis for the development of the definitive MOGA module, whose implementation will support large-size industrial plant models.