Ponente: Letitia Mirea, Associate Professor at the “Gheorghe Asachi”
Technical University of Iasi, Rumanía.
Fecha/hora: Martes 25 de septiembre, 11:30 horas.
Lugar: Seminario del Departamento de Informática e Ingeniería de Sistemas, edificio Ada Byron (Campus Río Ebro).
Resumen:
Fault diagnosis has been an active field of research for the past four decades due to an increased demand for safe and reliable operation of the technical processes. The fault diagnosis system has to perform the following tasks: fault detection (specify if something wrong happened in the process), fault isolation (identify the place where the fault appeared in the process) and fault evaluation (specify the amplitude and the time of occurrence of the fault). To achieve these goals, several techniques have been developed, that can be grouped in two main categories: model-based methods (a model of the diagnosed process is used to generate a set of residuals that are further analysed to decide if a fault occurred) and data-driven methods (the data collected from the sensors are directly analysed to detect the presence of an undesired behaviour). In this respect, the presentation will firstly refer to the particularities of some fault diagnosis methods. Then the talk will focus on two case studies that refer to the fault diagnosis of an evaporation station from a sugar factory and to the fault diagnosis of a wind turbine.
