Fault Detection in Engine Measurement Systems by a Model-Based Approach

In the engine development process many tests have to be carried out. Today’s measurement systems are of increasing complexity and usually automated; on the other hand, high accuracy is required in the measurements and usually failures on them are detected in the post-processing, resulting in important time and economic loss. Due to the huge amount of sensor signals, the on-line validation of the data is very time-consuming and infeasible without computer aid. In this study a failure detection framework is used for data plausibility analysis. Additionally, a useful set of physical equations applicable for failure detection in engine test benches is presented. These equations are combined with data-driven models allowing satisfactory detection rates while maintaining a low rate of false alarms. Validation results considering real-life data coming from engine test beds are included.