BACH 2: Bounded ReachAbility CHecker for Compositional Linear Hybrid Systems

Existing reachability analysis techniques are easy to fail when applied to large compositional linear hybrid systems, since their memory usages rise up quickly with the increase of systems' size. To address this problem, we propose a tool BACH 2 that adopts a path-oriented method for bounded reachability analysis of compositional linear hybrid systems. For each component, a path is selected and all selected paths compose a path set for reachability analysis. Each path is independently encoded to a set of constraints while synchronization controls are encoded as a set of constraints too. By merging all the constraints into one set, the path-oriented reachability problem of a path set can be transformed to the feasibility problem of this resulting linear constraint set, which can be solved by linear programming efficiently. Based on this path-oriented method, BACH 2 adopts a shared label sequence guided depth first search (SLS-DFS) method to perform bounded reachability analysis of compositional linear hybrid system, where all potential path sets within the bound limit are identified and verified one by one. By this means, since only the structure of a system and the recently visited one path in each component need to be stored in memory, memory consumption of BACH 2 is very small at runtime. As a result, BACH 2 enables the verification of extremely large systems, as is demonstrated in our experiments.