提出一种基于多智能体和神经网络的网络故障可视化诊断系统。每个被诊断的网络具有一个网络故障征兆收集智能体,负责收集并且预处理该网络的故障征兆信息,该信息被传送到位于诊断中心的网络故障诊断智能体,用作诊断及可视化。该系统的优点是网络故障诊断智能体可以以可视化的方式诊断网络的故障,并且动态监控网络的运行状态。试验结果证明所述系统的有效性和鲁棒性。 A network fault visual diagnosis system based on multi-agent and neural network is proposed. Each network being diagnosed has a network fault symptom collection agent responsible for collecting and pre-processing the network’s fault symptom information, which is transmitted to the network troubleshooting agent at the diagnostic center for diagnostics and visualization. The system has the advantage that the network fault diagnosis agent can visually diagnose the network fault and dynamically monitor the running status of the network. The experimental results demonstrate the effectiveness and robustness of the system.