多尺度变异粒子群优化MK-LSSVM的轴承寿命预测

被引:35
作者
张焱
汤宝平
熊鹏
机构
[1] 重庆大学机械传动国家重点实验室
基金
高等学校博士学科点专项科研基金;
关键词
寿命预测; 多尺度变异粒子群优化; 多核最小二乘支持向量机;
D O I
10.19650/j.cnki.cjsi.2016.11.011
中图分类号
TH133.33 [滚动轴承];
学科分类号
082805 [农业机械化与装备工程];
摘要
提出一种基于多尺度变异粒子群优化(MSPSO)算法和多核最小二乘支持向量机(MK-LSSVM)的预测新方法用于滚动轴承寿命预测。提取小波包相对能量特征对轴承性能衰退予以描述,提出MSPSO算法对MK-LSSVM模型参数进行优化选取,构造融合多核函数的LSSVM模型实现轴承寿命估计。MK-LSSVM中多核函数的引入克服了单核LSSVM对核函数类型强依赖性的弱点,MSPSO算法中种群全局大尺度均匀变异与个体局部邻域小尺度变异搜索联合策略的提出在增强种群多样性的同时保证了粒子群局部精确搜索的能力。利用实测滚动轴承振动数据分析,验证了所提MSPSO算法在模型参数优化及优化MKLSSVM模型在滚动轴承寿命预测应用中的有效性。
引用
收藏
页码:2489 / 2496
页数:8
相关论文
共 12 条
[1]
多峰函数优化的免疫云粒子群优化算法 [J].
吴建辉 ;
章兢 ;
陈华 ;
王东 ;
胡红平 .
仪器仪表学报, 2013, 34 (08) :1756-1765
[2]
一种多尺度协同变异的粒子群优化算法 [J].
陶新民 ;
刘福荣 ;
刘玉 ;
童智靖 .
软件学报, 2012, 23 (07) :1805-1815
[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]
An intelligent approach to machine component health prognostics by utilizing only truncated histories [J].
Lu, Chen ;
Tao, Laifa ;
Fan, Huanzhen .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2014, 42 (1-2) :300-313
[5]
Prediction of Mine Gas Emission Rate using Support Vector Regression and Chaotic Particle Swarm Optimization Algorithm [J].
Meng, Qian ;
Ma, Xiaoping ;
Zhou, Yan .
JOURNAL OF COMPUTERS, 2013, 8 (11) :2908-2915
[6]
A modified particle swarm optimization algorithm with applications [J].
He, Guang ;
Huang, Nan-jing .
APPLIED MATHEMATICS AND COMPUTATION, 2012, 219 (03) :1053-1060
[7]
A hierarchical multiple kernel support vector machine for customer churn prediction using longitudinal behavioral data [J].
Chen, Zhen-Yu ;
Fan, Zhi-Ping ;
Sun, Minghe .
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2012, 223 (02) :461-472
[8]
A multiple kernel support vector machine scheme for feature selection and rule extraction from gene expression data of cancer tissue [J].
Chen, Zhenyu ;
Li, Jianping ;
Wei, Liwei .
ARTIFICIAL INTELLIGENCE IN MEDICINE, 2007, 41 (02) :161-175
[9]
Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods.[J].Runqing Huang;Lifeng Xi;Xinglin Li;C. Richard Liu;Hai Qiu;Jay Lee.Mechanical Systems and Signal Processing.2005, 1
[10]
Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters [J].
Min, JH ;
Lee, YC .
EXPERT SYSTEMS WITH APPLICATIONS, 2005, 28 (04) :603-614