Generalized cross-signal anomaly detection on aircraft hydraulic system

Abstract

This paper outlines the mathematical foundation for a general method of anomaly detection from time-correlated sensor data. This method is a component of BEAM, but as an individual algorithm is capable of fault detection and partial classification. The method is applicable to a broad class of problems and is designed to respond to any departure from normal operation, including faults or events that lie outside the training envelope. We will also consider training of the detector and interface to a larger diagnostic system. Lastly we examine a brief illustration taken from aircraft testing that demonstrates the power and versatility of this method.