A Genetic Algorithm to enhance Observability and Redundancy Analysis in Instrumentation Design

CARBALLIDO JESSICA; PONZONI IGNACIO; BRIGNOLE NÉLIDA BEATRIZ

Paris, Francia

Congreso; IPMU 2006, XI International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems; 2006

In this paper a genetic algorithm to define a sensor network for instrumentation design (ID) is presented. The tool will be integrated in a decision support system (DSS) built to assist the engineer during the ID process. It considers four design objectives, and exhibits properties that were either never addressed by existing techniques or partially dealt with in the literature. The method’s performance was tested by carrying out the ID of an ammonia synthesis industrial plant. Results were statistically analysed. A face validity study on the fitness function’s soundness was also assessed by a chemical engineer with insight and expertise in this problem. The new technique performed satisfactorily, and therefore constitutes a promising method for its incorporation in the DSS.