非线性协整模型及其状态监测应用研究  

Nonlinear cointegration model with applications to condition monitoring

作　　者：鲁帆[1] 陈前[1] 

机构地区：[1]南京航空航天大学振动工程研究所,江苏南京210016

出　　处：《振动工程学报》2011年第5期468-472,共5页Journal of Vibration Engineering

摘　　要：基于线性协整理论的液压舵面伺服系统状态监测已经取得了积极的效果,但显示出对部分故障敏感性较弱的不足。为提高协整模型监测效力,研究采用基于神经网络的非线性协整建模方法,建立非平稳系统的非线性协整关系监测模型。仿真研究证实,该方法比线性协整监测模型具有更好的故障敏感性和可靠性。The linear cointegration theory has been successfully applied on a hydraulic servo system condition monitoring. But the insensitivity to some types of system faults hammered its application prospect. Therefore, a nonlinear cointegration method based on neural network is employed to build a nonlinear monitoring model for better performance. The simulation study has proofed that the nonlinear cointegration monitoring model is much more powerful and reliable than the linear one.

关 键 词：状态监测 非线性协整 液压伺服系统 神经网络 

分 类 号：TP206.3[自动化与计算机技术—检测技术与自动化装置]