Fault Diagnosis Systems

Abstract

Sensors and real apparatus are prone to faults that, in turn, affect the quality of retrieved data. Detection of faults or erroneous behaviors in sensor data stream must be anticipated to prevent drastic side effects (recall we make decisions out of incoming data). Cognitive fault diagnosis systems aim at detecting, identifying, and isolating the occurrence of faults without assuming that the process generating the data is known. It is shown that little can be done at the single sensor level unless strong hypotheses are made. However, the situation is different if the embedded system mounts a rich sensor platform or is inserted in a sensor network. In such a case, redundancy in the information content and functional dependencies among sensors can be exploited to classify a change as fault, a change in the environment or an inefficiency of the change detection method (model bias).