吉林大学学报(工学版) ›› 2014, Vol. 44 ›› Issue (4): 1010-1015.doi: 10.13229/j.cnki.jdxbgxb201404017

• • 上一篇    下一篇

EM算法的多重威布尔可靠性建模

王继利, 杨兆军, 李国发, 朱晓翠   

  1. 吉林大学 机械科学与工程学院, 长春 130022
  • 收稿日期:2013-02-28 出版日期:2014-07-01 发布日期:2014-07-01
  • 通讯作者: 李国发(1970-), 男, 教授, 博士生导师.研究方向:数控机床可靠性.E-mail:ligf@jlu.edu.cn
  • 作者简介:王继利(1987-), 男, 博士研究生.研究方向:数控机床可靠性.E-mail:wangjili1100@126.com
  • 基金资助:
    国家科技重大专项项目(2011ZX04014-011)

Reliability modeling of finite Weibull distribution based

on improved EM algorithm   

  1. WANG Ji-li, YANG Zhao-jun, LI Guo-fa, ZHU Xiao-cui
  • Received:2013-02-28 Online:2014-07-01 Published:2014-07-01

摘要: 以两参数威布尔分布为多重威布尔混合模型的基函数, 建立了以极大似然函数为目标的参数估计优化模型, 并改进了求解优化模型的EM算法。改进EM算法中提出贝叶斯随机分类方法, 用于初始化算法中的待估计参数。采用径向基函数插值法求解EM算法极大化步中的超越方程组, 并通过实际算例对比分析了改进EM算法与传统算法的准确性。给出了用改进EM算法求解多重威布尔混合模型参数的具体算例, 分析了多重威布尔混合模型的逼近性能。针对国内同期出厂的10台某型号冲压机床, 通过现场跟踪获取其初期故障样本数据, 运用多重威布尔混合模型研究可靠性数据分布规律, 并研究了KS检验统计量Dmax与威布尔混合模型重数N之间的关系。应用案例表明, 4重混合威布尔模型更能准确地反映冲压机床早期可靠性的实际分布规律。

关键词: 机械制造自动化, 机床可靠性, 多重威布尔混合模型, 最大似然法, EM算法, 贝叶斯随机分类, 径向基函数插值, KS检验

Abstract: Taking two-parameter Weibull distribution as the basis function, an optimization model is established based on the maximum likelihood method for parameter estimation, and the model is solved by improved Expectation-Maximization (EM) algorithm. Bayesian random classification algorithm, which is used for parameter initialization, is proposed in the improved EM algorithm. Radial basis function interpolation is used to solve the transcendental equation in the maximization step of the EM algorithm. The performance of the improved EM algorithm is compared with traditional algorithms by case study. Approximation performance of finite Weibull mixture distributions is analyzed with specific cases. The distribution law of the reliability data of ten punching machine tools, which come from testing field, is investigated by Weibull mixture distributions. The relationship between KS test statistic and the number of Weibull distributions is analyzed. The case study suggests that the fourfold Weibull mixture distributions could be better reflect the real law of the punching machine tools in early stage.

Key words: machinery manufacturing automation, reliability of machine tools, finite Weibull mixture distributions, maximum likelihood method, EM algorithm, Bayesian random classification, radial basis function interpolation, KS test

中图分类号: 

  • TG659
[1] Ginebra Josep, Sen Ananda. Minimax approach to accelerated life tests[J]. IEEE Transactions on Reliability, 1999, 47(3):30-37.
[2] 张英芝, 申桂香, 吴甦, 等. 随机截尾数控机床三参数威布尔分布模型[J].吉林大学学报:工学版, 2009, 39(2):378-381.[2] Zhang Ying-zhi, Shen Gui-xiang, Wu Su, et al. 3-parameter Weibull distribution for random truncated NC machine tool fault data[J]. Journal of Jilin University(Engineering and Technology), 2009, 39(2):378-381.
[3] 高顺川, 冯静, 孙权, 等. 基于威布尔分布的动态故障树定量分析方法[J].质量与可靠性, 2005, 119:28-31.
[4] Keller A Z, Kamath A R R. Reliability analysis of CNC machine tools[J].Reliab Eng, 1982, 3(6):449-473.
[5] 郑玉华, 王义强, 赵淑杰.CNC车床故障模式及其原因分析[J].系统工程理论与实践, 1997, 7:139-142.[5] Zheng Yu-hua, Wang Yi-qiang, Zhao Shu-jie.Failure mode and cause analysis of CNC lathe[J].Systems Engineering-Theory & Practice, 1997, 7:139-142.
[6] 姜华, 余群, 曹正清, 等. 基于随机过程理论的复杂可修系统可靠性规律研究[J].质量可靠性技术, 2000, 16(9):30-34.[6] Jiang Hua, Yu Qun, Cao Zheng-qing, et al. Studying reliability laws of complex maintainable system based on the stochastic processes[J]. Technology Supervision in Petroleum Industry, 2000, 16(9):30-34.
[7] Tan Fu-rong, Jiang Zhi-bin, Bai Tong-shuo.Reliability analysis of repairable systems using stochastic point processes[J].Journal of Shanghai Jiaotong University (Science), 2008, 13:366-369.
[8] Wang L Y, Cui L R, Yu M L. Markov repairable systems with stochastic regimes switching[J]. Journal of Systems Engineering and Electronics, 2011, 22:773-779.
[9] Jiang R, Murthy D N P. Reliability modeling involving two Weibull distributions[J]. Reliability Engineering and System Safety, 1995, 47:187-198.
[10] 凌丹, 黄洪钟, 张小玲.混合威布尔分布参数估计的L-M算法[J].电子科技大学学报, 2008, 37(4):634-640.[10] Ling Dan, Huang Hong-zhong, Zhang Xiao-ling.Parameters estimation for mixed Weibull distribution using L-M algorithm[J]. Journal of University of Electronic Science and Technology of China, 2008, 37(4):634-640.
[11] 高翔, 王若平, 夏长高, 等.随机变量多重Weibull统计模型及参数最优估计[J].农业机械学报, 2006, 37(11):41-44.[11] Gao Xiang, Wang Ruo-ping, Xia Chang-gao, et al. Multi-Weibull statistical model of random variables and optimal estimation of its parameters[J].Transactions of the Chinese Society for Agricultural Machinery, 2006, 37(11):41-44.
[12] Bucar T, Nagode M, Fajdiga M. Reliability approximation using finite Weibull mixture distributions[J]. Reliability Engineering and System Safety, 2004, 84(4):241-251.
[13] 穆雪峰, 姚卫星, 余雄庆, 等.多学科设计优化中常用代理模型的研究[J].计算力学学报, 2005, 22(5):608-612.[13] Mu Xue-feng, Yao Wei-xing, Yu Xiong-qing, et al. A survey of surrogate models used in MDO[J].Chinese Journal of Computational Mechanics, 2005, 22(5):608-612.
[1] 曲兴田, 赵永兵, 刘海忠, 王昕, 杨旭, 陈行德. 串并混联机床几何误差建模与实验[J]. 吉林大学学报(工学版), 2017, 47(1): 137-144.
[2] 任书楠, 杨向东, 王国磊, 刘志, 陈恳. 大部件喷涂中的移动机械臂站位规划[J]. 吉林大学学报(工学版), 2016, 46(6): 1995-2002.
[3] 沈志煌, 姚斌, 陆如升, 冯伟, 张祥雷, 王萌萌. 精密螺杆转子齿廓成形磨削的误差分析[J]. 吉林大学学报(工学版), 2016, 46(3): 831-838.
[4] 陈健, 葛连正, 李瑞峰. 考虑摩擦特性的机器人柔性关节鲁棒控制器设计[J]. 吉林大学学报(工学版), 2015, 45(6): 1906-1912.
[5] 王延忠, 侯良威, 吕庆军, 赵兴福, 吴灿辉. 基于总线控制的面齿轮复杂曲面加工技术[J]. 吉林大学学报(工学版), 2015, 45(6): 1836-1843.
[6] 郭黎滨, 张彬, 崔海, 张志航. 微细电火花线切割表面三维粗糙度的结构性参数[J]. 吉林大学学报(工学版), 2015, 45(3): 851-856.
[7] 匡哲君,师唯佳,胡亮. 基于无线传感器网络的角色成员关系剩余能量新算法[J]. 吉林大学学报(工学版), 2015, 45(2): 600-605.
[8] 周相超,薛睿,赵旦峰,付芳. 连续相位调制信号的载波相位软同步算法[J]. 吉林大学学报(工学版), 2015, 45(1): 291-296.
[9] 杨兆军,王继利,李国发,张新戈. 冲压机床可靠性增长的模糊层次分析预测方法[J]. 吉林大学学报(工学版), 2014, 44(3): 686-691.
[10] 佟金, 王亚辉, 卢纪生, 张书军, 陈东辉. 基于CCD的大型台阶轴锻件同轴度测量[J]. 吉林大学学报(工学版), 2013, 43(04): 945-950.
[11] 张雷, 赵云伟, 杨卓, 赵继. 电流变抛光液剪切屈服特性[J]. , 2012, 42(05): 1145-1150.
[12] 史永杰, 郑堤, 胡利永, 王龙山. 非球面件数控研抛力、研抛工具位置和姿态解耦技术[J]. 吉林大学学报(工学版), 2012, 42(01): 116-121.
[13] 张英芝1,郑锐2,申桂香1,王志琼1,李怀洋1,郑珊1. 基于Copula理论的数控装备故障相关性[J]. 吉林大学学报(工学版), 2011, 41(6): 1636-1640.
[14] 任迪, 王祖温, 包钢, 杨庆俊. 新型高刚度静压气体球轴承的静态特性[J]. 吉林大学学报(工学版), 2010, 40(06): 1599-1603.
[15] 李艳文, 马志强, 刘桂霞, 周春光. 基于EM的信号pathway重构[J]. 吉林大学学报(工学版), 2010, 40(05): 1303-1307.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!