Anomaly Detection in Electromechanical Systems Using Symbolic Dynamics

Major catastrophic failures in large scale engineering systems (e.g., aircraft, power plants and turbo-machinery) can possibly be averted if the malignant anomalies are detected at an early stage. This dissertation experimentally validates a novel method called Symbolic Time Series Analysis(STSA) for anomaly detection in electromechanical systems, derived from time series data of pertinent measured variable(s). In this dissertation, the performance of this anomaly detection method is compared with that of other existing pattern recognition techniques from the perspectives of early detection of fatigue damage in Al-2024. The experimental apparatus, on which the anomaly detection method is tested, is a multi-degree of freedom mass-beam structure excited by oscillatory motion of two electromagnetic shakers. The evolution of fatigue crack damage at one of the failure sites is detected from STSA of the pertinent sensor signal. Industrial Application-The dissertation presents STSA of bearing acceleration derived from a dynamic simulation model for detection and estimation of parametric changes in flexible disc/diaphragm couplings due to angular misalignment between shafts.