Hybrid Learning Approach to Sensor Fault Detection with Flight Test Data
Brian M. de Silva, Jared Callaham, Jonathan Jonker, Nicholas Goebel, Jennifer Klemisch, Darren McDonald, Nathan Hicks, J. Nathan Kutz, Steven L. Brunton, Aleksandr Y. Aravkin
Abstract
Data-driven algorithms are developed to fully automate sensor fault detection in systems governed by underlying physics, with a particular focus on the flight test setting. The proposed machine learning method uses a time series of typical behavior to approximate the evolution of measurements of interest by a linear time-invariant system. Given additional data from related sensors, a Kalman observer is used to maintain a separate real-time estimate of the measurement of interest. Sustained deviation between the measurements and the estimate is used to detect anomalous behavior. A decision tree, informed by integrating other sensor measurement values, is used to determine the amount of deviation required to identify a sensor fault. The method is validated by applying it to three test systems exhibiting various types of sensor faults: commercial flight test data, an unsteady aerodynamics model with dynamic stall, and a model for longitudinal flight dynamics forced by atmospheric turbulence. In the latter two cases, fault detection was tested for several prototypical failure modes. The combination of a learned dynamic model with the automated decision tree accurately detects sensor faults in each case.