Please wait a minute...
J4  2013, Vol. 47 Issue (6): 1013-1021    DOI: 10.3785/j.issn.1008-973X.2013.06.012
机械工程、能源工程     
基于免疫优化的产品系统可靠性参数区间预测方法
林晓华1,2, 冯毅雄1, 谭建荣1  
1. 浙江大学 流体传动及控制国家重点实验室,浙江 杭州 310027;
2. 南京工程学院 机械工程学院,江苏 南京 211167
Intervals prediction of system reliability parameters based on immune optimization
LIN Xiao-hua1,2, FENG Yi-xiong1, TAN Jian-rong1
1. State Key Laboratory of Fluid Power Transmission and Control, Zhejiang University, Hangzhou 310027, China; 2. College of Mechanical Engineering, Nanjing Institute of Technology, Nanjing 211167, China
 全文: PDF  HTML
摘要:

针对当前系统可靠性预测方法的不足,提出一种基于免疫优化的区间预测方法.构建可靠性参数预测神经网络模型,由极端学习机(ELM)算法进行训练,并以修正BFGS法对网络的左侧权值和阈值进行调整.在由该网络得到的预测点值和网络权重的基础上,根据非线性回归模型构建可靠性参数的区间预测值(PI),PI的质量取决于网络结构和权衰减调节参数.结合PI的覆盖率和平均区间比例长度提出一种新的PI综合评价指标,以此衡量PI的质量;引入免疫优化算法优化区间预测值和网络结构,以最小化综合评价指标为成本函数,寻求决策变量,即网络隐层神经元个数和权衰减调节参数的最优值.将提出的方法和理论应用于某系列数控车床的可靠性参数平均无故障时间的预测,证明了其预测性能优于传统方法.

Abstract:

Aiming at the deficiencies of system reliability prediction, an interval prediction method based on immune optimization algorithm was put forward. First, a prediction neural network of reliability parameters was constructed, which was trained by extreme learning machine (ELM) algorithm. The improved BFGS technique was used to optimize left weights and biases of the network. Then nonlinear regression model was used to construct prediction interval(PI) for reliability parameters based on its point value derived from the trained neural network and the weights of network. So the PI quality depends on the network structure and the weight decay regularizing factor. The immune algorithm was adopted to automate the neural network model selection and adjustment of the weight decay regularizing factor. Model selection and parameter adjustment were carried out through minimization of the PI based cost function called coverage and proportional length based criterion(CPLC), which combines the coverage probability and the mean interval proportional length of PI. Finally, the proposed theory and method was applied to predict the reliability parameter—mean time between failure(MTBF) of computer numerical control(CNC) lathes, which proved the that prediction performance of the method was better than that of the traditional methods.

出版日期: 2013-11-22
:  TH 122  
基金资助:

国家“973”重点基础研究发展计划资助项目(2011CB706500);国家自然科学基金资助项目(51175456,51275459).

通讯作者: 冯毅雄,男,副教授.     E-mail: fyxtv@zju.edu.cn
作者简介: 林晓华(1985—),女,博士生,主要从事产品设计、质量控制的研究. Email: zdlxh5001@yahoo.com.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

林晓华, 冯毅雄, 谭建荣. 基于免疫优化的产品系统可靠性参数区间预测方法[J]. J4, 2013, 47(6): 1013-1021.

LIN Xiao-hua, FENG Yi-xiong, TAN Jian-rong. Intervals prediction of system reliability parameters based on immune optimization. J4, 2013, 47(6): 1013-1021.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2013.06.012        http://www.zjujournals.com/eng/CN/Y2013/V47/I6/1013

[1] 于捷,石耀霖,张海龙,等. 基于Bayes方法的数控机床可靠性研究[J].机床与液压, 2009, 37(8): 251-253.

YU Jie, SHI Yaolin, ZHANG Hailong, et al. Study of CNC machine tools reliability based on Bayesian method [J]. Machine Tools & Hydraulics, 2009, 37(8): 251-253.

[2] HO S L, XIE M. The use of ARIMA models for reliability forecasting and analysis [J]. Computers & Industrial Engineering, 1998,35(1/2): 213-216.

[3] HO S L, XIE M, GOH T N. A comparative study of neural network and BoxJenkins ARIMA modeling in time series prediction [J]. Computers & Industrial Engineering, 2002,42 (24): 371-375.

[4] MOURA M D C, ZIO E, LINS I D, et al. Failure and reliability prediction by support vector machines regression of time series data [J]. Reliability Engineering & System Safety, 2011,96(11): 1527-1534.

[5] CHEN K Y. Forecasting systems reliability based on support vector regression with genetic algorithms [J]. Reliability Engineering & System Safety, 2007,92(4): 423-432.

[6] HU C H, SI X S, YANG J B. System reliability prediction model based on evidential reasoning algorithm with nonlinear optimization [J]. Expert Systems with Applications, 2010, 37(3): 2550-2562.

[7] KALOGIROU S. Articial neural networks in renewable energy systems: a review [J]. Renewable and Sustainable Energy Reviews, 2001,5 (4): 373-401.

[8] LOLAS S, OLATUNBOSUN O A. Prediction of vehicle reliability performance using artificial neural networks [J]. Expert Systems with Applications, 2008, 34(4): 2360-2369.

[9] XU K, XIE M, TANG LC, et al. Application of neural networks in forecasting engine systems reliability [J]. Applied Soft Computing, 2003,2(4): 255-268.

[10] 陈保家, 陈雪峰, 何正嘉, 等. 利用运行状态信息的机床刀具可靠性预测方法[J]. 西安交通大学学报, 2010,44(9): 74-77.

CHEN Baojia, CHEN Xuefeng, HE Zhengjia, et al. Operating condition informationbased reliability prediction of cutting tool [J]. Journal of Xi’an Jiaotong University, 2010,44(9): 74-77.

[11] 王蓓, 刘桥.优化BP神经网络的可靠性预测模型[J]. 计算机技术与发展, 2007, 17(9): 102-105.

WANG Bei, LIU Qiao. Credible prediction model based on BP neural network [J]. Computer Technology and Development, 2007, 17(9): 102-105.

[12] JAIN B A, NAG B N. performance evaluation of neural network decision models [J]. Journal of Management Information Systems,1997, 14(2): 201-216.

[13] HUANG G B, LI M B, CHEN L, et al. Incremental extreme learning machine with fully coMIPLex hidden nodes [J]. Neurocomputing, 2008,71(46): 576-583.

[14] WEI Z X, LI G Y, QI L Q. New quasinewton methods for unconstrained optimization problems [J]. Applied Mathematics and Computation, 2006,175(2): 1156-1188.

[15] HWANG J T G, DING A A. Prediction intervals for articial neural networks[J]. Journal of the American Statistical Association, 1997,92 (438): 748-757.

[16] VEAUX R D, SCHUMI J, SCHWEINSBERG J, et al. Prediction intervals for neural networks via nonlinear regression[J]. Technometrics,1998, 40 (4): 273-282.

[17] BISHOP C M. Neural networks for pattern recognition [M]. Oxford: Clarendon Press,1995.

[18] WANG H Y. Coverage probability of prediction intervals for discrete random variables [J]. Computational Statistics &Data Analysis, 2008,53(1): 17-26.

[19] 刘芳,梁雪峰.一种基于免疫算子的SVM算法[J].计算机科学, 2004, 31(2): 108-109.

LIU Fang, LIANG Xuefeng. An immune operation based SVM algorithm [J]. Computer Science, 2004,31(2): 108-109.

[20] 肖俊. 数控机床可靠性技术的分析与研究[D]. 上海:上海交通大学, 2007 .

XIAO Jun. Reliability technology analysis and research of CNC machine tools [D]. Shanghai: Shanghai Jiao Tong University, 2007.

[21] 余香梅,舒彤. 基于神经网络的数控机床可靠性预计研究[J]. 九江学院学报,2007(7): 40-43.

YU Xiangmei, SHU Tong. A study on the CNC reliability prediction based on neural networks[J]. Journal of Jiujiang University, 2007(7): 40-43.

[1] 杨巍,张秀峰,杨灿军,吴海杰. 基于人机5杆模型的下肢外骨骼系统设计[J]. J4, 2014, 48(3): 430-435.
[2] 刘征, 顾新建, 潘凯, 杨青海. 基于TRIZ的产品生态设计方法研究——融合规则和案例推理[J]. J4, 2014, 48(3): 436-444.
[3] 程吉祥,顾新建,代风,刘征. 基于BioTRIZ的产品创新设计过[J]. J4, 2014, 48(1): 35-41.
[4] 应征, 王青, 李江雄, 柯映林,孙文博,韩永伟. 飞机数字化装配系统运动数据集成及监控技术[J]. J4, 2013, 47(5): 761-767.
[5] 应征, 章明, 王青, 柯映林. 飞机大部件调姿机构磨损预测模型的构建与仿真[J]. J4, 2013, 47(2): 209-215.
[6] 刘曦泽, 祁国宁, 傅建中, 樊蓓蓓, 许静. 集成形态学矩阵与冲突解决原理的设计过程模型[J]. J4, 2012, 46(12): 2243-2251.
[7] 黄雪梅, 张磊安, 魏修亭. 兆瓦级风机叶片静力加载过程D-MFAC控制[J]. J4, 2012, 46(12): 2280-2284.
[8] 林晓华,冯毅雄,谭建荣. 产品方案设计约束模型及其演化博弈算法求解[J]. J4, 2012, 46(3): 533-541.
[9] 罗成对,冯毅雄,谭建荣,安相华. 基于语义PROMETHEE的产品设计方案群体多准则求解[J]. J4, 2012, 46(3): 524-532.
[10] 安相华,冯毅雄,谭建荣. 基于Choquet积分与证据理论的
产品方案协同评价方法
[J]. J4, 2012, 46(1): 163-169.
[11] 马志勇, 邱清盈, 冯培恩, 沈萌红, 曾令斌. 机械对称性的概念体系及其应用方法[J]. J4, 2010, 44(12): 2354-2359.
[12] 张秀芬, 张树有, 伊国栋. 产品多粒度层次可拆卸性评价模型与方法[J]. J4, 2010, 44(3): 581-588.
[13] 江伟光, 武建伟, 吴参, 等. 基于本体的产品知识集成[J]. J4, 2009, 43(10): 1801-1807.
[14] 刘海强, 纪杨建, 祁国宁, 等. 支持多学科设计优化的产品集成设计知识模型研究[J]. J4, 2009, 43(10): 1841-1847.
[15] 傅玉颖, 潘晓弘, 王正肖. 模糊合作博弈下的供应链多目标优化[J]. J4, 2009, 43(09): 1644-1648.