Automation of the SHIELD methodology for system hazard analysis and resilient design

The System Hazard Indication and Extraction Learning Diagnosis (SHIELD) methodology was developed as a novel method to perform system hazard analysis and resilient design. In an earlier paper we described SHIELD conceptually and outlined the details necessary to conduct the analysis manually. This approach integrates state space examination into the analysis process in order to facilitate efficient and comprehensive identification of undiscovered risks and hazard scenarios. SHIELD requires that three phases be performed serially to achieve a system hazard evaluation: decomposition, evaluation and prescription. The first phase of SHIELD, decomposition, breaks the system down hierarchically and recursively into smaller components so that the state space associated with each component is more manageable for the user. In the evaluation phase experts analyze the associated state space and transitions for each component, recursively, bottom-up. The prescription phase applies a set of heuristics to the results from the preceding phase to reduce system hazard. The main contribution of this paper is the automation of the methodology to reduce the effort used for analysis without sacrificing accuracy or overlooking hazardous state combinations. We describe in detail our automation concept and preliminary tests with the prototype.