Print Email Facebook Twitter Advanced Set Bounding Methods for Fault Detection Title Advanced Set Bounding Methods for Fault Detection Author Ritsma, Folkert (TU Delft Mechanical, Maritime and Materials Engineering) Contributor Ferrari, Riccardo (mentor) Al-Ars, Zaid (mentor) Degree granting institution Delft University of Technology Programme Mechanical Engineering | Systems and Control Date 2019-12-06 Abstract Performance of set based fault detection is highly dependent on the complexity of the set bounding methods used to bound the healthy residual set. Existing methods achieve robust performance with complex set bounding that narrowly define healthy system behavior, yet at the cost of higher computation times. In this thesis a major improvement is reached in both accuracy and computation time by applying machine learning methods to set bounding. A method is developed which achieves fault detection at several orders of magnitude the speed of an existing set based fault detection method without sacrificing a robust performance. Subject Fault DetectionMachine LearningAnomaly DetectionOutlier DetectionSupport Vector MachinesModel Based Fault DetectionSet Based Fault Detection To reference this document use: http://resolver.tudelft.nl/uuid:b6bad7a5-0afd-4268-873d-32a4a18b4281 Part of collection Student theses Document type master thesis Rights © 2019 Folkert Ritsma Files PDF mscThesis.pdf 4.99 MB Close viewer /islandora/object/uuid:b6bad7a5-0afd-4268-873d-32a4a18b4281/datastream/OBJ/view