Elektromekanik ve proses kontrol sistemleri için yeni veriye-dayalı hata tespiti

Fault Detection and Diagnosis (FDD) has become an attractive topic with increasing attention to improve efficiency, reliability and safety of modern engineering. The methodology used in FDD is clearly dependent on process and sort of available information, divided in two categories: model-based methods and data-driven-based methods. In the present research, observer-based and statistical information based Principal Component Analysis (PCA) method have been performed.PCA is a statistical process monitoring technique that has been widely used in industrial applications. PCA methods for Fault Detection (FD) use data collected from a steady-state process to monitor T2- and Q- statistics with a fixed threshold. For the systems where transient values of the processes must be taken into account, the usage of fixed threshold in PCA method causes false alarms and missing data that significantly compromise the reliability of the monitoring systems. In this thesis, two new methods based on PCA are proposed to overcome false alarms which occur in the transient states according to changing process conditions and the missing data problem. The proposed methods are implemented and validated experimentally on an electromechanical and process control system.