A new belief rule base based distributed online fault diagnosis method for multi-agent systems

In this paper, based on belief rule base (BRB), we studied the distributed online fault diagnosis problem of multi-agent systems (MASs). To begin with, considering the distributed nature of MASs, by using the relative information between an agent and its neighbors, a distributed online fault diagnosis model is constructed. Next, for the results of fault diagnosis, when an agent doesn't get enough relative information to diagnose the fault, the fault diagnosis result may be inaccurate, and if there exist too many neighbors of an agent, the number of attributes of the proposed BRB fault diagnosis model will be too large, which will lead to large computation. To improve the performance of the proposed distributed online fault diagnosis model, a real-time communication topology switching strategy was proposed. Under the constructed distributed fault diagnosis model, the real-time performance and the accuracy of fault diagnosis for agents can be guaranteed simultaneously. Finally, a simulation is given to validate the effectiveness and advancement of the distributed online fault diagnosis method proposed in this paper.