Predictive Safety Analytics for Complex Aerospace Systems

Abstract

The complexity of the National Airspace System (NAS) in the United States presents a number of novel and unique challenges for the integration of Unmanned Aircraft Systems (UAS). In particular, one challenging aspect is the modeling of UAS safety risk for civil applications given the scarcity of actual operational data. With the creation of a probabilistic model, inferences about changes to the states of the accident shaping or causal factors can be drawn quantitatively. These predictive safety inferences derive from qualitative reasoning to plausible conclusions based on data, assumptions, and/or premises and enable an analyst to identify the most prominent causal factors leading to a risk factor prioritization. Such an approach also facilitates the study of possible mitigation effects. This paper illustrates the development of an Object-Oriented Bayesian Network (OOBN) to integrate the safety risks contributing to a notional “lost link” scenario for a small UAS (sUAS) with the mission of aerial surveying for a bridge infrastructure inspection. As a System of Systems (SoS) approach, an OOBN facilitates decomposition at the sub-system level yet enables synthesis at a higher-order systems level. In essence, the methodology serves as a predictive safety analytics platform to support reasoning to plausible conclusions from assumptions or premises.