Model-based Tools and Techniques for Real-Time System and Software Health Management

Abstract

The ultimate challenge in system health management is the theory for and application of the technology to systems, for instance to an entire vehicle. The main problem the designer faces is complexity; simply the sheer size of the system, the number of data points, anomalies, and failure modes can be overwhelming. Furthermore, systems are heterogeneous and one has to have a systems engineertextquoterights view to understand interactions among systems. Yet, system-level health management is crucial, as faults increasingly arise from system-level effects and interactions. While individual subsystems tend to have built-in redundancy or local anomaly detection, fault management, and prognostics features, the system integrators are 287required to provide the same capabilities for the entire vehicle, across different engineering subsystems and areas.

Publication
Machine Learning and Knowledge Discovery for Engineering Systems Health Management