An approach for diagnosability analysis and sensor placement for continuous processes based on evolutionary algorithms and analytical redundancy

Rubén Leal (1) , Jose Aguilar (2, 3) , Louise Travé-Massuyès (4) , Edgar Camargo (1) , Addison Ríos (3)

1 PDVSA - Petroleos de Venezuela
2 CEMISID
3 ULA - Universidad de Los Andes [Mérida, Venezuela]
4 LAAS-DISCO - Équipe DIagnostic, Supervision et COnduite

In this work we propose to use an approach based on genetic algorithms to obtain analytical redundancy relations to study the diagnosability property on a given continuous system, and if this not fulfill, our approach allows studying the sensor placement problem in order to fulfill it. The redundancy relations are based on the minimal test equation support and in a structural analysis over a bipartite graph. The faults analysis is studied using a multi-objective fitness function in two genetic algorithms which describe the different constraints to be covered in order to reach the diagnosability property on the system. Additionally, our approach allows studying the sensors placement problem on systems that do not fulfill the detectability or isolability properties, using another genetic algorithm. 2126 Rubén Leal et al.

Mots clés: Bipartite Graph; Genetic Algorithm; Structural Analysis; Sensors Placement; Diagnosability

Domaines: Intelligence artificielle [cs.AI]; Automatique

Rubén Leal, Jose Aguilar, Louise Travé-Massuyès, Edgar Camargo, Addison Ríos. An approach for diagnosability analysis and sensor placement for continuous processes based on evolutionary algorithms and analytical redundancy. International Journal of Applied Mathematical Sciences, 2015, 9 (43), pp.2125 - 2146. ⟨10.12988/ams.2015.52122⟩. ⟨hal-01701569⟩