Task reliability assessment method for autonomous intelligent system based on multi-agent approach

Objectives Aiming at the problems that the task reliability of autonomous intelligent system is difficult to accurately evaluate due to the characteristics of decoupling of components, changing system states and complex fault propagation laws, this paper proposes a multi-agent based task reliability evaluation method for autonomous intelligent system. MethodsBy constructing a reliability simulation framework based on double-layer network structure, the separation expression and coupling correlation of information propagation process and fault propagation process of autonomous intelligent system are realized. By designing the attributes, behaviors and interfaces of various components in the autonomous intelligent system, a universal fault propagation and state switching mechanism is built. Based on the analysis of the factors affecting the task reliability of autonomous intelligent system, the multi-stage task success criterion is established. Based on Anylogic simulation platform, the task reliability evaluation model of autonomous intelligent system with the capability of single process simulation and multiple Monte Carlo simulation is developed. Results The simulation results show that the proposed method can realize the quantitative evaluation of the reliability of typical tasks of intelligent autonomous systems, and can explore the key fault factors affecting the task reliability of intelligent autonomous systems.Conclusions The proposed method is c to realize the state perception and capability autonomous organization of autonomous intelligent system.