基于Copula函数的齿轮箱剩余寿命预测方法  

Prediction method for the remaining useful life of gearbox based on copula function

作　　者：宋仁旺[1] 张岩 石慧[1] SONG Renwang;ZHANG Yan;SHI Hui(School of Electronic and Information Engineering,Taiyuan University of Science and Technology,Taiyuan 030024,China)

机构地区：[1]太原科技大学电子信息工程学院,太原030024

出　　处：《系统工程理论与实践》2020年第9期2466-2474,共9页Systems Engineering-Theory & Practice

基　　金：国家自然科学基金青年科学基金项目(61703297);山西省青年科学基金(201601D021065);校博士启动基金(20152022)。

摘　　要：齿轮箱是风力发电机组的关键部件,对风力发电机的整体寿命有直接影响.针对齿轮箱的剩余寿命,提出了一种多退化量下的剩余寿命预测方法.首先,在分析齿轮箱寿命的影响因素基础上,选取齿轮箱的振动加速度和噪声作为退化量;其次,采用基于核估计和随机滤波理论的方法分别对齿轮箱的振动加速度和噪声进行建模,从而获得齿轮箱的剩余寿命概率密度函数,进而得到其边缘分布函数;再利用Copula函数表示齿轮箱的振动加速度和噪声之间的随机相关性,求得齿轮箱剩余寿命的联合分布函数,从而得到齿轮箱剩余寿命的联合概率密度函数,得到齿轮箱剩余寿命预测值;最后,提出基于赤池信息准则模型评价的Copula函数选择方法.通过齿轮箱的试验验证了该方法的有效性.The gearbox is a key component of the wind turbine and has a direct impact on the overall life of the wind turbine.Aiming at the remaining useful life of gearbox,a remaining useful life prediction method under multi-degenerate quantity is proposed.Firstly,on the basis of analyzing the influencing factors of gearbox life,the vibration acceleration and noise of gearbox are selected as the degradation quantity,and secondly,the vibration acceleration and noise of gearbox are modeled by means of kernel estimation and stochastic filtering theory respectively,so as to obtain the the remaining useful life probability density function of gearbox,and then obtain its edge distribution function.The copula function is used to represent the stochastic correlation between the vibration acceleration and the noise of the gearbox,and the joint distribution function of the remaining useful life of the gearbox is obtained,and the combined probability density function of the remaining useful life of the gearbox is obtained,and the remaining useful life prediction value of the gearbox is obtained.Finally,a copula function selection method based on red pool information criterion model evaluation is proposed.The effectiveness of this method is verified by the test of gearbox.

关 键 词：剩余寿命预测 多退化变量建模 COPULA函数 

分 类 号：TP202.1[自动化与计算机技术—检测技术与自动化装置]