A Case Study On The Application of Software Health Management Techniques

As commercial aircraft increasingly rely on integrated modular avionics where software implements safety-critical functions, the ability to diagnose and mitigate software faults in real-time becomes essential for maintaining aircraft safety. This work innovates by developing practical techniques to model complex software systems and automatically generate health managers that can detect subtle faults missed by traditional testing. The model-based approach enables diagnosis of latent software defects that may escape rigorous verification and testing during development.

This work presents a comprehensive case study applying software health management techniques to the Boeing 777 Air Data Inertial Reference Unit using timed failure propagation graphs for real-time fault diagnosis. The authors develop models of the ADIRU software architecture using the ARINC Component Model and apply component-level health management to detect anomalies in individual processing modules. The framework integrates formal methods for specifying monitoring conditions and uses event-based anomaly detection with timed state machines to diagnose faults in real-time.

The case study demonstrates successful detection and diagnosis of injected faults in an emulated ADIRU system using the component framework and monitoring-based approach. Results show that the system can identify specific component failures and characterize their effects on system output through timed fault propagation analysis. The code generation tools successfully produce runtime code that performs health monitoring with acceptable performance overhead while maintaining strict timing properties required for real-time avionics.