FAULT-DETECTION AND ISOLATION FOR AN EXPERIMENTAL INTERNAL-COMBUSTIONENGINE VIA FUZZY IDENTIFICATION

Certain engine faults can be detected and isolated by examining the pa ttern of deviations of engine signals from their nominal unfailed valu es. In this brief paper, we show how to construct a fuzzy identifier t o estimate the engine signals necessary to calculate the deviation fro m nominal engine behavior, so that we may determine if the engine has certain actuator and sensor ''calibration faults.'' We compare the fuz zy identifier to a nonlinear ARMAX technique and provide experimental results showing the effectiveness of our fuzzy identification based fa ilure detection and identification strategy.