作　　者： ; ;

机构地区： 江西理工大学

出　　处： 《中国钨业》 2005年第5期38-41,共4页

摘　　要： 针对神经网络极易陷入局部极小的问题,提出变尺度混沌优化方法与神经网络相结合的变尺度混沌神经网络综合模型,讨论变尺度混沌神经网络模型的建模思路及其算法实现;介绍球磨机常见的故障类型,建立球磨机故障诊断的变尺度混沌神经网络模型,并进行仿真试验,结果表明:该模型具有较高的预测精度,可以有效地运用于球磨机诊断中的故障预测。 A fusion model of mutative scale chaos neural network by means of mutative scale chaos optimization method and neural network is propsed to overcome problems in make-up local minima of neural network. The idea of building model based on mutative scale chaos neural network is discussed. The types of faults of grinding machine are described. The mutative chaos neural network model in fault diagnosis of grinding machine is built and the simulation test is made. The result shows that the model has a high accuracy and it can forecast the fault diagnosis of grinding machine effectively.

关 键 词： 混沌 神经网络 球磨机 故障诊断

领　　域： [自动化与计算机技术] [自动化与计算机技术] [自动化与计算机技术] [自动化与计算机技术]