Addressing challenges of hazard analysis in systems of systems

Hazards are situations that can result in accidents. Depending on the domain, this can include loss of lives, injuries and economic or environmental disasters. For example, a common hazard in the aviation domain is in flight engine shutdown. Hazard analysis is the process of discovering hazards in a system. This activity has been performed for many years in safety engineering and is a straightforward activity in most domains. In recent years a new class of systems has emerged, distinguished from traditional (monolithic) systems by a combination of characteristics such as autonomous and independently developed components, increased complexity and geographic dispersion. These characteristics introduce a number of challenges for traditional hazard analysis. This paper describes these challenges and proposes two complementary approaches that address them: dependability deviation analysis (DDA) and simulation-based hazard analysis (SimHAZAN). The paper then describes a model-driven approach that combines the two and thereby provides an underlying framework for their application during system development.