On the design of context-aware health monitoring without a priori knowledge; an AC-Motor case-study

Health monitoring without a priori knowledge can save a significant amount of design and implementation time. However, for smaller devices with limited available resources, this is not feasible using most conventional methods. For small footprint sensor and actuator devices, we propose a health monitoring architecture and algorithm, which uses context-awareness to assess the health status of an “Injective-function Black-Box” without having a priori knowledge about it. The proposed algorithm can identify normal modes of operation, change of states (operation modes), deviation from a state, and abnormal functional operation. We have tested the algorithm on an AC Motor where the system was able to identify its health and changes in the operation status accordingly.