Health Monitoring Framework for Aircraft Engine System using Deep Neural Network

Abstract

A real-time monitoring framework is developed to detect operational anomalies in aircraft engine performance. A historical flight dataset recorded from commercial aircraft is utilized to perform the proposed method. Sampling frequency synchronization and denoise are performed on the flight dataset using signal processing techniques. A robust detection algorithm using the deep neural network is developed to capture flight performance anomalies that show significant off-nominal behavior in engine related and flight dynamic features. The accuracy and efficiency of the proposed monitoring method are validated through a demonstration of anomaly detection in the aircraft engine system associated with dynamic flight behavior.

CAE‐WANN: A novel anomaly detection method for gas turbines via search space extension

“…9 As an important branch of machine learning, artificial neural networks (ANNs) have attracted increasing attention in anomaly detection and fault diagnosis for gas turbines in recent years. [10][11][12][13][14][15] For example, Fu et al 11 employed a stacked denoising autoencoder (SDAE) to extract features from raw data for yielding high detection accuracy. Yuan et al 15 applied a Long short-term memory (LSTM) neural network for fault diagnosis of the aero-engine, which got a good diagnosis in the case of strong noises.…”

“…However, the machine learning method can extract features from real‐life monitoring data without understanding the operating mechanism of gas turbines 9 . As an important branch of machine learning, artificial neural networks (ANNs) have attracted increasing attention in anomaly detection and fault diagnosis for gas turbines in recent years 10–15 . For example, Fu et al 11 .…”