基于改进PSO-模糊神经网络旋转机械设备故障诊断研究  

Application of Fuzzy Neural Network Based on Improved PSO Algorithm to Fault Diagnosis of Rotating Machinery

作　　者：孙鹏伟 侯国安[1] SUN Peng-wei;HOU Guo-an(Yinchuan Energy College,Ningxia Yinchuan 750015,China)

机构地区：[1]银川能源学院,宁夏银川750015

出　　处：《广州化工》2023年第24期107-110,共4页GuangZhou Chemical Industry

基　　金：宁夏区级大学生创新训练项目(项目号:S202213820007)。

摘　　要：对旋转机械设备故障进行准确预测最主要的是要提高评价模型的性能,模糊神经网络具有很好的泛化能力和学习能力,但易陷入局部最优解,不能得到最优的故障类型。利用改进的粒子群算法对模糊神经网络的惯性权重和隶属度参数进行优化,极大地提高了模糊神经网络的性能,在旋转机械故障诊断和预测中发挥了极为重要作用。The most important thing to accurately predict the faults of rotating machinery equipment is to improve the performance of the evaluation model.Fuzzy neural network has good generalization ability and learning ability,but it is easy to fall into the local optimal solution and cannot get the optimal fault type.The improved particle swarm optimization algorithm was used to optimize the inertia weight and membership parameters of the fuzzy neural network,which greatly improved the performance of the fuzzy neural network and played an extremely important role in the fault diagnosis and prediction of rotating machinery.

关 键 词：改进PSO算法 模糊神经网络 旋转机械设备 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]