A sequential diagnostic strategy generation transformation method for large-scale systems based on multi-signal flow graph model and multi-objective optimization

Abstract

The multi-signal flow graph model is widely used in sequential fault diagnosis of complex systems due to its low modeling difficulty and fast diagnostic speed. Based on this model, testers can obtain a strategy to guide the diagnosis by solving the optimal sequential strategy generation problem (OSP). As system complexity increases, diagnostic requirements for various costs are increasingly highlighted, and the optimization problem also evolves from small-scale single-objective OSP to large-scale multi-objective OSP (LM-OSP). However, due to the complexity of the objective space and the Markov property of decision variables, LM-OSP is challenging to solve with conventional algorithms. To address this, this paper transforms the original LM-OSP into a more tractable designated region mapping problem (DRMP) and solves it with swarm intelligence search algorithms (SISAs) for better solutions. First, distributions are approximated to make the objective space continuous. Second, the decision space is linearized by converting the spatial data structure. Based on the continuity and linearization, the transformed DRMP is established, and basic steps for applying any SISA are determined. Finally, strategies with a comprehensive 8∼10-fold diagnostic performance improvement can be achieved in simulation and real case experiments.