Avionic Main Fuel Pump Simulation and Fault-Diagnosis Benchmark
📰 ArXiv cs.AI
Learn to simulate and diagnose faults in avionic main fuel pumps using physics-informed co-simulation and machine learning algorithms
Action Steps
- Build a high-fidelity simulation model of an avionic main fuel pump system using MATLAB/Simulink Simscape Fluids
- Generate time-series data from the simulation model to train anomaly detection and diagnosis algorithms
- Configure and test machine learning algorithms for fault diagnosis using the generated data
- Apply the trained algorithms to real-world data to evaluate their performance
- Compare the results of different algorithms and simulation models to identify the most effective approach
Who Needs to Know This
Aerospace engineers and researchers working on anomaly detection and diagnosis in cyber-physical systems can benefit from this benchmark to improve their algorithms and models
Key Insight
💡 Physics-informed co-simulation can generate high-quality data for training anomaly detection and diagnosis algorithms in cyber-physical systems
Share This
Simulate and diagnose faults in avionic main fuel pumps with physics-informed co-simulation and ML algorithms #avionics #faultdiagnosis #machinelearning
Key Takeaways
Learn to simulate and diagnose faults in avionic main fuel pumps using physics-informed co-simulation and machine learning algorithms
Full Article
Title: Avionic Main Fuel Pump Simulation and Fault-Diagnosis Benchmark
Abstract:
arXiv:2604.22869v1 Announce Type: cross 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. 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-serie
Abstract:
arXiv:2604.22869v1 Announce Type: cross 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. 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-serie
DeepCamp AI