基于AIC优化RBF网络的机床主轴轴承磨损状态分析  

State Analysis for the Abrasion of the Headstock Bearing Based on the RBF Neural Network Optimized by AIC

作　　者：黄强[1] 张晓[1] 丁志华[1] 

机构地区：[1]九江学院,江西九江332005

出　　处：《机床与液压》2011年第21期168-170,共3页Machine Tool & Hydraulics

基　　金：江西省自然科学基金项目(2008GQC0002);江西省教育厅科技资助项目(GJJ08448)

摘　　要：利用赤迟信息准则(AIC)确定RBF神经网络的隐含层节点数和中心,建立基于该神经网络的机床磨损状态分析模型,并利用实验获取的振动信号来判断机床主轴轴承磨损状况。实验及仿真结果表明:基于AIC的RBF网络技术的分析方法在机床磨损状态分析中是有效可行的,对单一磨损状态的正确识别率达到了97.5%,对其他复杂机械的振动分析同样具有参考价值。The AIC was used to calculate the number and center of nodes of the RBF neural network. The analysis model for the machine＇s states was built. The vibration signals were used to estimate the abrasion states of the headstock bearing. The experiment and simulation results show that the state analysis method with RBF neural network based on AIC is effective. The veracity of identification is 97. 5% to the single fault. It has valuable reference to the vibration analysis for other complex machines.

关 键 词：机床 赤迟信息准则(AIC) RBF神经网络 状态分析 

分 类 号：TK42[动力工程及工程热物理—动力机械及工程]