Avionic Main Fuel Pump Simulation and Fault-Diagnosis Benchmark
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.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Machine Learning arXiv:2604.22869 (cs) [Submitted on 23 Apr 2026] Title:Avionic Main Fuel Pump Simulation and Fault-Diagnosis Benchmark Authors:Felix Leonhard Janzen, Lukas Moddemann, Alexander Diedrich, Oliver Niggemann View a PDF of the paper titled Avionic Main Fuel Pump Simulation and Fault-Diagnosis Benchmark, by Felix Leonhard Janzen and 3 other authors View PDF HTML (experimental) Abstract: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.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI