Uncertainty Quantification for Full-Flight Data Based Engine Fault Detection with Neural Networks

Abstract

Current state-of-the-art engine condition monitoring is based on a minimum of one steady-state data point per flight. Due to the scarcity of available data points, there are difficulties distinguishing between random scatter and an underlying fault introducing a detection latency of several flights. Today’s increased availability of data acquisition hardware in modern aircraft provides continuously sampled in-flight measurements, so-called full-flight data. These full-flight data give access to sufficient data points to detect faults within a single flight, significantly improving the availability and safety of aircraft. Artificial neural networks are considered well suited for the timely analysis of an extensive amount of incoming data. This article proposes uncertainty quantification for artificial neural networks, leading to more reliable and robust fault detection. An existing approach for approximating the aleatoric uncertainty was extended by an Out-of-Distribution Detection in order to take the epistemic uncertainty into account. The method was statistically evaluated, and a grid search was performed to evaluate optimal parameter combinations maximizing the true positive detection rates. All test cases were derived based on in-flight measurements of a commercially operated regional jet. Especially when requiring low false positive detection rates, the true positive detections could be improved 2.8 times while improving response times by approximately 6.9 compared to methods only accounting for the aleatoric uncertainty.