Avionic Main Fuel Pump Simulation and Fault-Diagnosis Benchmark
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913059624189952 |
|---|---|
| author | Janzen, Felix Leonhard Moddemann, Lukas Diedrich, Alexander Niggemann, Oliver |
| author_facet | Janzen, Felix Leonhard Moddemann, Lukas Diedrich, Alexander Niggemann, Oliver |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_22869 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Avionic Main Fuel Pump Simulation and Fault-Diagnosis Benchmark Janzen, Felix Leonhard Moddemann, Lukas Diedrich, Alexander Niggemann, Oliver Machine Learning Artificial Intelligence Systems and Control 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. |
| title | Avionic Main Fuel Pump Simulation and Fault-Diagnosis Benchmark |
| topic | Machine Learning Artificial Intelligence Systems and Control |
| url | https://arxiv.org/abs/2604.22869 |