Fault Diagnosis and Prognosis using a Hybrid Approach combining Structural Analysis and Data-driven Techniques

This paper presents a fault diagnosis and prognosis based on an hybrid approach that combines structural and data-driven techniques. The proposed method involves two phases. Firstly, the residuals structure is obtained from the structural model of the system using structural analysis without using mathematical models (only the component description of the system). Secondly, the analytical expressions of residuals are obtained from available historical data using a robust identification approach. The diagnosis part consists in checking the evolution of residuals during the process, any inconsistency of residuals can be considered as a fault, so that the thresholds for each residual are introduced. The residuals are obtained using the identified interval model that takes into account the uncertainty and noises affecting the system. Once the fault is detected, also it is possible to determine which fault occurred in the system using the FSM (Fault Signature Matrix) obtained from the structural analysis of the system and residual generation. The prognosis part is developed using the same steps, but instead of considering the actual situation, it evaluates the tendency of deviation respect the nominal operation condition to predict the future residual inconsistency, allowing estimating the RUL (Remaining Useful Life) of the system. The interval model is also introduced for the future prediction of residuals, thus there will be an interval of RUL for each residual which contains the maximum and minimum RUL values. The proposed approach is applied to a brushless DC motor (BLDC) used as a case study. Simulation experiments illustrate the performance of the approach.