基于支持向量机和卡尔曼滤波的机械零件剩余寿命预测模型研究

被引：85

作者：

于震梁

孙志礼

曹汝男

王鹏

机构：

[1] 东北大学机械工程与自动化学院

来源：

兵工学报 | 2018年 / 39卷 / 05期

关键词：

机械零件; 剩余寿命; 支持向量机; 非线性卡尔曼滤波; 置信区间;

D O I：

暂无

中图分类号：

TH17 [机械运行与维修];

学科分类号：

120111 [工业工程];

摘要：

现有机械零件剩余寿命预测模型在建模过程中,无法同时采用已有数据库数据及被预测产品实时退化数据,为了弥补其不足,提出一种支持向量机(SVM)和非线性卡尔曼滤波相结合的机械零件剩余寿命预测模型。根据现有全寿命试验数据训练所得的SVM回归模型,建立非线性卡尔曼滤波状态更新方程,依据机械零件退化特征构造时间更新方程,设定初始剩余寿命值及其方差,通过逐步迭代计算各时刻剩余寿命估计值及一定置信水平的置信区间。该计算模型能够充分利用现有零件与同类零件全寿命试验数据和被预测零件的实时状态退化数据,实现剩余寿命预测。以某型号滚动轴承为例,验证了所提出剩余寿命预测模型的精度、稳定性及工程应用价值。

引用

页码：991 / 997

页数：7

共 14 条

[1]

支持向量机与卡尔曼滤波算法在组合导航中的应用研究 [D].

陈磊琛 .

中国地质大学,

2010

[2]

A review on prognostic techniques for non-stationary and non-linear rotating systems.[J].Man Shan Kan;Andy C.C. Tan;Joseph Mathew.Mechanical Systems and Signal Processing.2015,

[3]

Prognostics and Health Management: A Review on Data Driven Approaches.[J].Kwok L. Tsui;Nan Chen;Qiang Zhou;Yizhen Hai;Wenbin Wang;Shaomin Wu.Mathematical Problems in Engineering.2015,

[4]

Fatigue crack growth estimation by relevance vector machine [J].

Zio, Enrico ;

Di Maio, Francesco .

EXPERT SYSTEMS WITH APPLICATIONS, 2012, 39 (12) :10681-10692

[5]

Bearing fault prognosis based on health state probability estimation.[J].Hack-Eun Kim;Andy C.C. Tan;Joseph Mathew;Byeong-Keun Choi.Expert Systems With Applications.2011, 5

[6]

Improving ability of tele-operators to complete progressively more difficult mobile robot paths using simple expert systems and ultrasonic sensors [J].

Sanders, David A. ;

Graham-Jones, Jasper ;

Gegov, Alexander .

INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION, 2010, 37 (05) :431-440

[7]

Application of relevance vector machine and logistic regression for machine degradation assessment.[J].Wahyu Caesarendra;Achmad Widodo;Bo-Suk Yang.Mechanical Systems and Signal Processing.2009, 4

[8]

Estimation and forecasting of machine health condition using ARMA/GARCH model.[J].Hong Thom Pham;Bo-Suk Yang.Mechanical Systems and Signal Processing.2009, 2

[9]

Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics.[J].Hai Qiu;Jay Lee;Jing Lin;Gang Yu.Journal of Sound and Vibration.2005, 4

[10]

A Contextualized Historical Analysis of the Kuhn–Tucker Theorem in Nonlinear Programming: The Impact of World War II.[J].Tinne Hoff Kjeldsen.Historia Mathematica.2000, 4

← 1 2 →