Avionic Main Fuel Pump Simulation and Fault-Diagnosis Benchmark
This work provides a much-needed benchmark dataset for fault diagnosis in safety-critical aviation systems, where real data is scarce.
The paper introduces a high-fidelity, physics-informed co-simulation of an aircraft main-fuel-pump system and generates annotated time-series data for anomaly detection and fault diagnosis. The benchmark is demonstrated with unsupervised RNN-VAE and SOM-VAE models that separate healthy and faulty conditions.
In many cyber-physical systems, especially in critical applications such as aeroplanes, data to train anomaly detection and diagnosis algorithms is lacking due to data protection issues and partial observability. To combat this inherent lack of data, we introduce a high-fidelity, physics-informed co-simulation of a common aircraft main-fuel-pump system modelled in \textsc{MATLAB/Simulink Simscape Fluids}. We also describe its generated time-series data with health and fault mode annotations. To show feasibility of our benchmark, we apply an unsupervised Recurrent Variational Autoencoder (RNN-VAE) for anomaly detection and a SOM-VAE for operating mode discretization, trained to separate healthy and faulty conditions.