In-flight Novelty Detection with Convolutional Neural Networks

Abstract

Gas turbine engines are complex machines that typically generate a vast amount of data, and require careful monitoring to allow for cost-effective preventative maintenance. In aerospace applications, returning all measured data to ground is prohibitively expensive, often causing useful, high value, data to be discarded. The ability to detect, prioritise, and return useful data in real-time is therefore vital. This paper proposes that system output measurements, described by a convolutional neural network model of normality, are prioritised in real-time for the attention of preventative maintenance decision makers.Due to the complexity of gas turbine engine timevarying behaviours, deriving accurate physical models is difficult, and often leads to models with low prediction accuracy and incompatibility with real-time execution. Data-driven modelling is a desirable alternative producing high accuracy, asset specific models without the need for derivation from first principles.We present a data-driven system for online detection and prioritisation of anomalous data. Biased data assessment deriving from novel operating conditions is avoided by uncertainty management integrated into the deep neural predictive model. Testing is performed on real and synthetic data, showing sensitivity to both real and synthetic faults. The system is capable of running in real-time on low-power embedded hardware and is currently in deployment on the Rolls-Royce Pearl 15 engine flight trials.

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

“…Since the approximation of the aleatoric uncertainty according to [32] has already been successfully applied to in-flight measurements, it is used as starting point for further improvement. The approximation of the aleatoric uncertainty introduces additional model complexity to the neural network by requiring an increased number of output nodes.…”

“…The aleatoric uncertainty can be evaluated by approximating the probability density functions of individual measurements with artificial neural networks [31]. Despite an existing concept for approximating the aleatoric uncertainty for full-flight engine data [32], there is no method taking both the aleatoric and epistemic uncertainty into account.…”

“…Apart from the proven capability of the above listed artificial neural networks to model the steady-state and transient performance of gas turbines, there is additionally existing research in uncertainty quantification for neural networks. One existing method for approximating the aleatoric uncertainty in [32] is extended by an Out-of-Distribution Detection for additionally taking the epistemic uncertainty into account. The proposed approach is then tested utilizing full-flight data of a commercially operated regional jet.…”

Construction of Data-Driven Performance Digital Twin for a Real-World Gas Turbine Anomaly Detection Considering Uncertainty

“…Currently, most airlines adopted Quick Access Recorders (QAR) for data acquisition, providing flight data continuously sampled at frequencies of 1 Hz and more, which is also referred to as full-flight data covering the whole flight. The availability of these data obtained from a large variety of sensors enables the introduction of new methodologies to assess engine condition, which offers the chance to detect engine faults within one flight more reliably to support more efficient in-service operations and maintenance decisions [ 6 , 7 ]. An approach for fault detection based on steady-state flight regimes of full-flight data is demonstrated in [ 8 , 9 ].…”

“…Hartwell et al propose a practical and computationally inexpensive method for in-flight real-time anomaly detection based on a convolutional neural network. The efficacy of the method has been demonstrated on both real-time-series and synthetic snapshot data [ 7 ].…”