Finite safety models for high-assurance systems

Preventing bad things from happening to engineered systems, demands improvements to how we model their operation with regard to safety. Safety-critical and fiscally-critical systems both demand automated and exhaustive verification, which is only possible if the models of these systems, along with the number of scenarios spawned from these models, are tractably finite. To this end, this dissertation ad dresses problems of a model's tractability and usefulness. It addresses the state space minimization problem by initially considering tradeoffs between state space size and level of detail or fidelity. It then considers the problem of human interpretation in model capture from system artifacts, by seeking to automate model capture. It introduces human control over level of detail and hence state space size during model capture. Rendering that model in a manner that can guide human decision making is also addressed, as is an automated assessment of system timeliness. Finally, it addresses state compression and abstraction using logical fault models like fault trees, which enable exhaustive verification of larger systems by subsequent use of transition fault models like Petri nets, timed automata, and process algebraic expressions. To illustrate these ideas, this dissertation considers two very different applications - web service compositions and submerged ocean machinery.