为了提高煤矿通风机故障诊断的准确性,采用了一种粒子群优化RBF神经网络的方法。利用粒子群容易实现等特点,对RBF网络的中心、宽度以及连接权重进行优化,并用优化好的神经网络对通风机进行故障诊断。仿真结果表明,该方法具有较好的分类效果,适用于通风机的故障诊断,是一种实用的故障诊断方法。 In order to improve the accuracy of coal mine ventilator fault diagnosis, a particle swarm optimization RBF neural network method is adopted. By using particle swarm optimization and so on, the center, width and connection weight of RBF network are optimized. The optimized neural network is used to diagnose the fan. The simulation results show that this method has good classification effect and is suitable for the fault diagnosis of ventilator. It is a practical fault diagnosis method.