Model Abstraction for Discrete-Event Systems Using a SAT Solver

Model abstraction for finite state automata is beneficial to reduce the complexity of discrete-event systems (DES), enhance the readability and facilitate the control synthesis and verification of DES. Supremal quasi-congruence computation is an effective way for reducing the state space of DES. Effective algorithms on the supremal quasi-congruence relation have been developed based on the graph theory. This paper proposes a new approach to translate the supremal quasi-congruence computation into a satisfiability (SAT) problem that determines whether there exists an assignment for Boolean variables in the state-to-coset allocation matrix. If the result is satisfied, then the supremal quasi-congruence relation exists and the minimum equivalence classes is obtained. Otherwise, it indicates that there is no such supremal quasi-congruence relation, and a new set of observable events needs to be modified or reselected for the original system model. The satisfiability problem on the computation of supremal quasi-congruence relation is solved by different methods, which are respectively implemented by mixed integer linear programming (MILP) in MATLAB, binary linear programming (BLP) in CPLEX, and a SAT-based solver (Z3Py). Compared with the MILP and BLP methods, the SAT method is more efficient and stable. The computation time of model abstraction for large-scale systems by Z3Py solver is significantly reduced.

Automated summary

Model abstraction is important for reducing the complexity of discrete-event systems (DES) and enhancing their readability. This paper proposes a new approach to compute the supremal quasi-congruence relation using satisfiability (SAT) problem. The SAT method is more efficient and stable compared to other methods like mixed integer linear programming (MILP) and binary linear programming (BLP).