Browsing by Subject "Fault diagnosis"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Early diagnosis of breakdown through transfer learning
    (2019-05) Özbek, Seren
    Breakdown prediction of equipment is an essential task considering the management of resources and maintenance operations. Early diagnosis systems allow creating alerts on time for taking precautions on production. A significant challenge for diagnosis is to have an insufficient size of data, yet, transfer learning approaches can alleviate such an issue when there is a constrained supply of training data. We intend to improve the reliability of breakdown prediction when there is a limited quantity of training data. We recommend similarity correlation on Remaining Useful Life of these equipment. To do this, we offer learning a common feature space between the target and the source equipment, where we acquire prior knowledge from the source that has different measurements than the target. Within the learned joint feature matrices, we train our model on the vast amount of data of different equipment and finetune it using the data of our target equipment. In this way, we aim to obtain an accurate and reliable model for early breakdown prediction.
  • Thumbnail Image
    ItemOpen Access
    Robust fault detection by simultaneous observers
    (2000) Ammar, Nejib
    This thesis addresses the problem of fault detection and isolation in linear systems based on unknown input observers. Functional disturbance decoupled observers which estimate specified or unspecified linear functions of system states regardless of the disturbances are first studied. Necessary and sufficient condition for the existence of such observers are presented. The investigation is extended to simultaneous disturbance decoupled observers where multiple systems are observed by a single disturbance decoupled observer. The application of disturbance decoupled observers to fault detection and diagnosis are explicitly outlined, and a new scheme that is based on simultaneous unknown input observers is proposed to enhance the already existing schemes. Finally, a detailed simulation example is carried out to examine the utility of the proposed scheme.