Modelling and Analysis of Fire Sprinklers by Verifying Dynamic Fault Trees

We study the reliability analysis of fire sprinkler systems. We show that the characteristic features of Dugan's dynamic fault trees (DFTs) such as spare management, temporal ordering of failures and functional dependencies, are natural and adequate mechanisms to model various relevant phenomena in realistic fire sprinklers. For DFT analysis, we employ probabilistic model checking, an automated technique to assess reliability along with correctness. This is to date the most scalable, numerical DFT analysis technique. We show how standard reliability measures of fire sprinkler systems can be efficiently computed using the Storm model checker. In addition, we consider metrics beyond standard reliability, e.g., the probability to fail without going through a degradation phase and the worst-case reliability achieved after degradation. We illustrate our approach by fire sprinkler systems in shopping centers.