Dynamic data-driven learning for self-healing avionics

In sensor-based systems, spatio-temporal data streams are often related in non-trivial ways. For example in avionics, while the airspeed that an aircraft attains in cruise phase depends on the weight it carries, it also depends on many other factors such as engine inputs, angle of attack, and air density. It is therefore a challenge to develop failure models that can help recognize errors in the data, such as an incorrect fuel quantity or an incorrect airspeed. In this paper, we present a highly-declarative programming framework that facilitates the development of self-healing avionics applications, which can detect and recover from data errors. Our programming framework enables specifying expert-created failure models using error signatures, as well as learning failure models from data. To account for unanticipated failure modes, we propose a new dynamic Bayes classifier, that detects outliers and upgrades them to new modes when statistically significant. We evaluate error signatures and our dynamic Bayes classifier for accuracy, response time, and adaptability of error detection. While error signatures can be more accurate and responsive than dynamic Bayesian learning, the latter method adapts better due to its data-driven nature.