FAULT DETECTION FRAMEWORK FOR IMBALANCED AND SPARSELY-LABELED DATA SETS USING SELF-ORGANIZING MAPS

dc.contributor.advisorPecht, Michael G.en_US
dc.contributor.authorShah, Rushiten_US
dc.contributor.departmentMechanical Engineeringen_US
dc.contributor.publisherDigital Repository at the University of Marylanden_US
dc.contributor.publisherUniversity of Maryland (College Park, Md.)en_US
dc.date.accessioned2018-09-19T05:33:17Z
dc.date.available2018-09-19T05:33:17Z
dc.date.issued2018en_US
dc.description.abstractWhile machine learning techniques developed for fault detection usually assume that the classes in the training data are balanced, in real-world applications, this is seldom the case. These techniques also usually require labeled training data, obtaining which is a costly and time-consuming task. In this context, a data-driven framework is developed to detect faults in systems where the condition monitoring data is either imbalanced or consists of mostly unlabeled observations. To mitigate the problem of class imbalance, self-organizing maps (SOMs) are trained in a supervised manner, using the same map size for both classes of data, prior to performing classification. The optimal SOM size for balancing the classes in the data, the size of the neighborhood function, and the learning rate, are determined by performing multiobjective optimization on SOM quality measures such as quantization error and information entropy; and performance measures such as training time and classification error. For training data sets which contain a majority of unlabeled observations, the transductive semi-supervised approach is used to label the neurons of an unsupervised SOM, before performing supervised SOM classification on the test data set. The developed framework is validated using artificial and real-world fault detection data sets.en_US
dc.identifierhttps://doi.org/10.13016/M2MS3K512
dc.identifier.urihttp://hdl.handle.net/1903/21420
dc.language.isoenen_US
dc.subject.pqcontrolledMechanical engineeringen_US
dc.subject.pquncontrolledFault detectionen_US
dc.subject.pquncontrolledImbalanced dataen_US
dc.subject.pquncontrolledmachine learningen_US
dc.subject.pquncontrolledSelf organizing mapen_US
dc.subject.pquncontrolledsemi-supervised learningen_US
dc.subject.pquncontrolledSparsely-labeled dataen_US
dc.titleFAULT DETECTION FRAMEWORK FOR IMBALANCED AND SPARSELY-LABELED DATA SETS USING SELF-ORGANIZING MAPSen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Shah_umd_0117N_19423.pdf
Size:
3.37 MB
Format:
Adobe Portable Document Format