Distributed multi-agent cooperative fault detection method, storage medium and equipment

Abstract

The invention discloses a distributed multi-agent collaborative fault detection method, a storage medium and distributed multi-agent collaborative fault detection equipment. The distributed multi-agent collaborative fault detection method comprises the following steps of: constructing a multi-agent system fault detection reference model; designing a fault self-detection algorithm for each node inthe multi-agent system fault detection reference model to obtain a fault self-detection result; correcting the multi-agent system fault detection reference model according to the fault self-detectionresult, optimizing a cooperative mechanism among nodes, and forming a cooperative detection network; and constructing a distributed residual generator based on the collaborative detection network, designing a corresponding threshold function to evaluate residuals, acquiring a fault mutual detection result, and determining that the multi-agent system fails by combining the fault self-detection result and the fault mutual detection result. According to the distributed multi-agent collaborative fault detection method, the multi-agent cooperative fault can be detected under the condition that onlyneighbor relative output information is obtained, the calculation complexity is low, and interference can be suppressed to the maximum extent while the detection precision is guaranteed.

Description

technical field [0001] The invention relates to the technical field of multi-agent control, in particular to a distributed multi-agent cooperative fault detection method, storage medium and equipment. Background technique [0002] In recent years, multi-agent systems are constantly developing in the direction of large-scale, strong coupling, and high complexity. Problems to be solved. However, the multi-agent system itself is a complex distributed nonlinear autonomous system, and the system usually needs to face complex external environments, such as strong electromagnetic interference, targeted attack and trapping by the enemy, etc., which will affect the failure the normal operation of the algorithm. In addition, the normal operation of the algorithm also needs the information interaction between nodes, and the complex and limited external environment often makes the absolute output value of the nodes unobtainable. For example, in the battlefield environment of complex ...

AI Technical Summary

Problems solved by technology

[0006] In view of the deficiencies in the prior art above, the purpose of the present invention is to provide a distributed multi-agent cooperative fault detection method, storage medium and equipment, aiming to solve the problem of undetectable faults caused by relative output information and single-node performance in the prior art. The problem of low reliability of detection results caused by restrictions

Images