Physics-Guided Neural Network Model for Aeroengine Control System Sensor Fault Diagnosis under Dynamic Conditions

Abstract

Sensor health assessments are of great importance for accurately understanding the health of an aeroengine, supporting maintenance decisions, and ensuring flight safety. This study proposes an intelligent framework based on a physically guided neural network (PGNN) and convolutional neural network (CNN) to diagnose sensor faults under dynamic conditions. The strength of the approach is that it integrates information from physics-based performance models and deep learning models. In addition, it has the structure of prediction–residual–generation-fault classification that effectively decouples the interaction between sensor faults and system state changes. First, a PGNN generates the engine’s non-linear dynamic prediction output because the PGNN has the advantage of being able to handle temporal information from the long short-term memory (LSTM) network. We use a cross-physics–data fusion scheme as the prediction strategy to explore the hidden information of the physical model output and sensor measurement data. A novel loss function that considers physical discipline is also proposed to overcome the performance limitations of traditional data-driven models because of their physically inconsistent representations. Then, the predicted values of the PGNN are compared with the sensor measurements to obtain a residual signal. Finally, a convolutional neural network (CNN) is used to classify faults for residual signals and deliver diagnostic results. Furthermore, the feasibility of the proposed framework is demonstrated on an engine sensor fault dataset. The experimental results show that the proposed method outperforms the pure data-driven approach, with the predicted RMSE being reduced from 1.6731 to 0.9897 and the diagnostic accuracy reaching 95.9048%, thereby confirming its superior performance.

Gas turbine aero engine fault detection using Geo-TLSVM and digital twin with multimodal data analysis

“…The aircraft systems are first developed with DT for analysis. The power source of the aircraft is the AE, and the working of this AE has great effects on the aircraft safety [4,5]. The AE operates with high temperature, pressure, rotation, and strong vibration [6].…”

A Proton Flux Prediction Method Based on an Attention Mechanism and Long Short-Term Memory Network

“…In recent years, deep learning methods have made significant progress in handling time series data for this issue. These methods include Convolutional Neural Networks (CNN) [9][10][11], ARMA Neural Networks [12], and Long Short-Term Memory Networks (LSTM) [13][14][15], among others [16]. For instance, L Wei et al [17] used a Long Short-Term Memory Network (LSTM) to develop a model for predicting daily > 2 MeV electron integral flux in geostationary orbit.…”

A Reduced Order Model for Monitoring Aeroengines Condition in Real Time

“…Purely data-driven methods [16] rely on just data and are usually based on machine learning and statistical algorithms. Their online operation is fairly inexpensive, but constructing these models requires offline training [17], the computational cost of which is usually enormous. It is performed using former experience in the type of engine that is being analyzed.…”