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

doi:10.3969/j.issn.1000-1093.2018.05.020

兵工学报 ›› 2018, Vol. 39 ›› Issue (5): 991-997.doi: 10.3969/j.issn.1000-1093.2018.05.020

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

于震梁, 孙志礼, 曹汝男, 王鹏

（东北大学机械工程与自动化学院，辽宁沈阳 110819）

收稿日期:2017-08-14 修回日期:2017-08-14 上线日期:2018-06-22
通讯作者: 孙志礼(1957—)，男，教授，博士生导师 E-mail:zhlsun@mail.neu.edu.cn
作者简介:于震梁（1982—），男，博士研究生。E-mail:yuzhenliang_neu@163.com
基金资助:
国家自然科学基金项目（51775097）

Research on Remaining Useful Life Predictive Model of Machine Parts Based on SVM and Kalman Filter

YU Zhen-liang, SUN Zhi-li, CAO Ru-nan, WANG Peng

(School of Mechanical Engineering and Automation, Northeastern University, Shenyang 110819, Liaoning, China)

Received:2017-08-14 Revised:2017-08-14 Online:2018-06-22

摘要/Abstract

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。

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

Abstract: A new remaining useful life (RUL) predictive model for machine parts is proposed, which combines support vector machine (SVM) and non-linear Kalman filter. The proposed model is expected to fix the awkward situation in that the degradation data from both database and the predicted part cannot be used at the same time by most of the exiting RUL models. The SVM regression model trained by data from full-life tests is treated as the status update equation of non-linear Kalman filter. The time update equation is constructed according to the degradation characteristics of machine parts. RUL estimations and corresponding confidence intervals of point-in-time are computed iteratively after setting the initial RUL value and its variance. The proposed model makes the best use of data from both full-life tests of the same or similar parts and current part during its degradation. The accuracy of RUL estimation, the stability and practical values of the proposed model are illustrated by analyzing a certain type of antifriction bearings. Key

Key words: machinepart, remainingusefullife, supportvectormachine, non-linearKalmanfilter, confidenceinterval

中图分类号:

TB114.37

于震梁, 孙志礼, 曹汝男, 王鹏. 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[J]. 兵工学报, 2018, 39(5): 991-997.

YU Zhen-liang, SUN Zhi-li, CAO Ru-nan, WANG Peng. Research on Remaining Useful Life Predictive Model of Machine Parts Based on SVM and Kalman Filter[J]. Acta Armamentarii, 2018, 39(5): 991-997.

参考文献

［1］ Tsui K L, Chen N, Zhou Q, et al. Prognostics and health management: a review on data driven approaches［J］. Mathematical Problems in Engineering, 2015(6): 1-17.
［2］ Kan M S, Tan A C C, Mathew J. A review on prognostic techniques for non-stationary and non-linear rotating systems［J］. Mechanical Systems and Signal Processing, 2015, 62/63:1-20.
［3］ Hong T P, Yang B S. Estimation and forecasting of machine health condition using ARMA/GARCH model［J］. Mechanical Systems and Signal Processing, 2010, 24(2):546-558.
［4］ Lei Y G, Li N P, Lin J. A new method based on stochastic process models for machine remaining useful life prediction［J］.IEEE Transactions on Instrumentation and Measurement, 2016, 65(12): 2671-2684.
［5］ Sanders D A, Graham-Jones J, Gegov A. Improving ability of tele-operators to complete progressively more difficult mobile robot paths using simple expert systems and ultrasonic sensors［J］. Industrial Robot, 2010, 37(5):431-440.
［6］ Malhi A, Yan R, Gao R X. Prognosis of defect propagation based on recurrent neural networks［J］. IEEE Transactions on Instrumentation and Measurement, 2011, 60(3):703-711.
［7］ Kim H E, Tan A C C, Mathew J, et al. Bearing fault prognosis based on health state probability estimation［J］. Expert Systems with Applications, 2012, 39(5): 5200-5213.
［8］ Caesarendra W, Widodo A, Yang B S. Application of relevance vector machine and logistic regression for machine degradation assessment［J］. Mechanical Systems and Signal Processing, 2010, 24(4):1161-1171.
［9］ Zio E, Maio F D. Fatigue crack growth estimation by relevance vector machine［J］. Expert Systems with Applications, 2012, 39(12): 10681-10692.

［10］ Sun F Q, Li X Y, Jiang T M, et al. A Bayesian least-squares support vector machine method for predicting the remaining useful life of a microwave component［J］.Advances in Mechanical Engineering, 2017, 9(1): 1-9.
［11］ Maior C B S, Moura M D C, Lins I D, et al. Remaining useful life estimation by empirical mode decomposition and support vector machine［J］. IEEE Latin America Transactions, 2016, 14(11): 4603-4610.
［12］朱征宇, 刘琳, 崔明. 一种结合SVM与卡尔曼滤波的短时交通流预测模型［J］. 计算机科学, 2013, 40(10):248-251.
ZHU Zheng-yu, LIU Lin, CUI Ming. Short-term traffic flow forecasting model combining SVM and Kalman filtering ［J］. Computer Science, 2013, 40(10): 248-251. (in Chinese)
［13］陈磊琛. 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］. 武汉：中国地质大学, 2010.
CHEN Lei-chen. Research on support vector machine and its application in integrated navigation with Kalman filter ［D］. Wuhan：China University of Geosciences, 2010. (in Chinese)
［14］杨茂, 黄宾阳, 江博,等. 基于卡尔曼滤波和支持向量机的风电功率实时预测研究［J］. 东北电力大学学报, 2017, 37(2): 45-51.
YANG Mao, HUANG Bin-yang, JIANG Bo, et al. Real-time prediction for wind power based on Kalman filter and support vector machines ［J］. Journal of Northeast Electric Power University,2017, 37(2):45-51. (in Chinese)
［15］ Kjeldsen T H. A contextualized historical analysis of the Kuhn-Tucker theorem in nonlinear programming: the impact of World War II［J］. Historia Mathematica, 2000, 27(4):331-361.
［16］刘学艺，李平，郜传厚. 极限学习机的快速留一交叉验证算法［J］. 上海交通大学学报, 2011, 45(8): 1140-1145.
LIU Xue-yi, LI Ping, GAO Chuan-hou. Fast leave-one-out cross-validation algorithm for extreme learning machine［J］. Journal of Shanghai Jiao Tong University, 2011, 45(8): 1140-1145. (in Chinese)
［17］ Lin C J, Weng R C. Simple probabilistic predictions for support vector regression［R］. Taipei: National Taiwan University, 2004.
［18］ Qiu H, Lee J, Lin J, et al. Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics［J］. Journal of Sound & Vibration, 2006, 289(4):1066-1090.
［19］申中杰，陈雪峰，何正嘉，等. 基于相对特征和多变量支持向量机的滚动轴承剩余寿命预测［J］. 机械工程学报，2013,49（2）： 183-189.
SHEN Zhong-jie, CHEN Xue-feng, HE Zheng-jia, et al. Remaining life predictions of rolling bearing based on relative features and multivariable support vector machine ［J］.Journal of Mecha-nical Engineering, 2013, 49(2): 183-189. (in Chinese)

第39卷
第5期2018 年5月兵工学报ACTA
ARMAMENTARIIVol.39No.5May2018

[1]	段浩，陈晖，翟兆阳，韩雨，马凡华，崔亚辉. 基于支持向量机的氢混天然气发动机性能预测[J]. 兵工学报, 2022, 43(5): 1002-1011.
[2]	杨建新，兰小平，冯亚东，杨一铭，郭志明. 基于改进樽海鞘群和最小二乘支持向量机算法的新型弹药质量评估方法[J]. 兵工学报, 2022, 43(5): 1012-1022.
[3]	李良钰，苏铁熊，马富康，吴小军，徐春龙. 基于集合经验模态分解-支持向量机的高压共轨系统故障诊断方法[J]. 兵工学报, 2022, 43(5): 992-1001.
[4]	许晓东，唐圣金，谢建，于传强，王凤飞，韩洋洋. 随机退化应力作用下设备剩余寿命预测方法[J]. 兵工学报, 2022, 43(3): 712-719.
[5]	马润波，董丽虹，王海斗. 基于支持向量机的热喷涂层接触疲劳寿命预测[J]. 兵工学报, 2021, 42(12): 2743-2752.
[6]	雷震烁，刘松涛，温镇铭，葛杨. 复杂电磁环境下末制导雷达工作状态实时判别方法[J]. 兵工学报, 2021, 42(1): 83-90.
[7]	王成，吴岩，杨廷飞. 利用改进单分类支持向量机提升舰船尾流目标的检测准确率[J]. 兵工学报, 2020, 41(9): 1887-1893.
[8]	吕国俊，曹建军，郑奇斌，常宸，翁年凤，彭琮. 基于多目标蚁群优化的单类支持向量机相似重复记录检测[J]. 兵工学报, 2020, 41(2): 324-331.
[9]	于军，刘可，郭帅，于广滨，郭振宇. 基于条件深度循环生成对抗网络和动作探索的行星轮轴承剩余寿命预测[J]. 兵工学报, 2020, 41(11): 2170-2178.
[10]	邓青，薛青，罗佳. 基于支持向量机的坦克驾驶模拟训练结果分析[J]. 兵工学报, 2019, 40(9): 1953-1960.
[11]	代健，李泽，郝新红，栗苹. 基于目标联合特征提取的脉冲多普勒引信抗干扰方法[J]. 兵工学报, 2019, 40(2): 225-233.
[12]	谢萌蕤，赵兆，李阳，许志勇. 基于多尺度子带能量集特征的膛口波识别方法[J]. 兵工学报, 2018, 39(10): 1951-1957.
[13]	刘小平，张立杰，沈凯凯，高强. 考虑测量误差的步进加速退化试验建模与剩余寿命估计[J]. 兵工学报, 2017, 38(8): 1586-1592.
[14]	帅勇，宋太亮，王建平，沈洪. 一种改进的装备保障能力并联预测模型[J]. 兵工学报, 2016, 37(6): 1089-1095.
[15]	张彪，闫晓鹏，栗苹，李志强，池庆玺. 基于支持向量机的无线电引信抗扫频式干扰研究[J]. 兵工学报, 2016, 37(4): 635-640.

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

Research on Remaining Useful Life Predictive Model of Machine Parts Based on SVM and Kalman Filter

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价