|本期目录/Table of Contents|

[1]赵江平,丁洁,陈敬龙.基于GM-SVR的小样本条件下化工设备可靠性预测[J].中国安全生产科学技术,2019,15(1):145-150.[doi:10.11731/j.issn.1673-193x.2019.01.023]
　ZHAO Jiangping,DING Jie,CHEN Jinglong.Reliability prediction of chemical equipment under small sample condition based on GM and SVR[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2019,15(1):145-150.[doi:10.11731/j.issn.1673-193x.2019.01.023]
点击复制

基于GM-SVR的小样本条件下化工设备可靠性预测
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
15
期数:
2019年1期
页码:
145-150
栏目:
职业安全卫生管理与技术
出版日期:
2019-01-31

文章信息/Info

Title:
Reliability prediction of chemical equipment under small sample condition based on GM and SVR
文章编号:
1673-193X(2019)-01-0145-06
作者:
赵江平; 丁洁; 陈敬龙
（西安建筑科技大学 资源工程学院，陕西 西安 710055）
Author(s):
ZHAO Jiangping;  DING Jie;  CHEN Jinglong
(College of Resources Engineering, Xi’an University of Architecture and Technology, Xi’an Shaanxi 710055, China)
关键词:
化工设备; 小样本; GM（1; 1）; 支持向量回归机; 可靠性
Keywords:
chemical equipment;  small sample;  GM(1; 1);  support vector regression machine (SVR);  reliability
分类号:
X937
DOI:
10.11731/j.issn.1673-193x.2019.01.023
文献标志码:
A
摘要:
为了准确预测化工设备可靠性趋势，针对化工设备失效寿命数据为小样本的情形，基于灰色估计法与支持向量回归机在小样本数据处理中的优势，建立了失效寿命时间服从三参数威布尔分布的化工设备可靠性模型；结合GM（1，1）和SVR对模型进行参数估计，在压缩机可靠性分析中进行了实例应用，对比分析了最小二乘法、灰色估计法和GM-SVR的估计效果。研究结果表明：GM-SVR对威布尔分布参数的估计精度明显优于最小二乘法和灰色估计法，可以有效地应用于化工设备失效数据为小样本时的可靠性预测。
Abstract:
In order to predict the trend of the reliability of chemical equipment accurately, aiming at the situation that the failure life data of chemical equipment are the small sample, a model for the reliability of chemical equipment with the failure life data obeying the threeparameter Weibull distribution was established based on the advantages of grey estimation method and support vector regression machine (SVR) in the data processing of small sample. The parameters estimation of the model was carried out by combining GM(1,1) with SVR, then the example application was conducted on the reliability analysis of compressor, and the estimation effect of the least square method, grey estimation method and GM-SVR were compared and analyzed. The results showed that the estimation accuracy of GM-SVR model for the parameters with Weibull distribution was obviously better than those of the least square method and grey estimation method, which can be effectively applied to the reliability prediction of chemical equipment with the failure data as small sample.

参考文献/References:

［1］徐子军, 王海清, 陈韬婕, 等. 基于蒙特卡罗的石化设备寿命均值估计优化与应用［J］. 中国安全科学学报, 2016, 26(5):70-75. XU Zijun, WANG Haiqing, CHEN Taojie, et al. Optimization of petrochemical equipment MTTF estimation based on Monte Carlo and its application ［J］. China Safety Science Journal, 2016, 26(5): 70-75.
［2］裴峻峰, 许军, 郑庆元, 等. 以可靠性为中心的往复式压缩机维修方法研究［J］. 石油工业技术监督, 2015, 31(11):69-73. PEI Junfeng, XU Jun, ZHENG Qingyuan, et al. Study on repair method of reciprocating compressor based on reliability ［J］. Technology Supervision in Petroleum Industry, 2015, 31(11): 69-73.
［3］徐子军. 基于失效模式的非完全寿命数据分析方法研究［D］. 青岛:中国石油大学(华东), 2016.
［4］宋明顺, 鲁伟, 方兴华. 基于小样本失效数据的机械可靠性评估［J］. 工业工程, 2017, 20(5): 87-93. SONG Mingshun, LU Wei, FANG Xinghua. A research on mechanical reliability assessment based on small sample failure data ［J］. Industrial Engineering Journal, 2017, 20(5): 87-93.
［5］金星, 彭博, 鲁海, 等. 小样本条件下可靠寿命的蒙特卡罗评估方法［J］. 弹箭与制导学报, 2012, 32(2): 217-218，222. JIN Xing, PENG Bo, LU Hai, et al. Monte Carlo assessment method for reliable life with small samples ［J］. Journal of Projectiles, Rockets, Missiles and Guidance, 2012, 32(2): 217-218，222.
［6］马宪民, 杨洁, 张永强. 基于粒子群优化的矿用减速器可靠性寿命预测分析［J］. 煤炭技术, 2017, 36(3): 237-239. MA Xianmin, YANG Jie, ZHANG Yongqiang. Life prediction reliability analysis of mine reducer based on particle swarm optimization ［J］. Coal Technology, 2017, 36(3): 237-239.
［7］丁飞, 金鑫, 王春华, 等.小样本事件下液压支架可靠性评估［J］. 煤炭科学技术, 2016, 44(11): 116-120. DING Fei, JIN Xin, WANG Chunhua, et al. Evaluation on reliability of hydraulic powered support under small sample event ［J］. Coal Science and Technology, 2016, 44(11): 116-120.
［8］何旭, 姜宪国, 张沛超, 等. 基于SVM的小样本条件下继电保护可靠性参数估计［J］. 电网技术, 2015, 39(5):1432-1437. HE Xu, JIANG Xianguo, ZHANG Peichao, et al. SVM based parameter estimation of relay protection reliability with small samples ［J］. Power System Technology, 2015, 39(5): 1432-1437.
［9］李晓雨. 三参数Weibull分布参数估计方法研究［D］.北京：北京交通大学, 2012.
［10］NAGATSUKA H , KAMAKURA T . A consistent method of estimation for the three-parameter Weibull distribution ［J］. Computational Statistics and Data Analysis, 2013, 58: 210-226.
［11］辛龙, 周越文, 翟颖烨, 等. 基于Weibull分布的航空装备部件寿命预测研究［J］. 电光与控制, 2014, 21(12):102-105. XIN Long, ZHOU Yuewen, ZHAI Yingye, et al. Weibull distribution based lifetime prediction for components of aerial equipments ［J］. Electronics Optics & Control, 2014, 21(12): 102-105.
［12］史景钊, 陈新昌, 张峰. 基于Matlab和GM(1,1)模型的Weibull分布参数估计［J］. 江西科学, 2010, 28(3): 291-294. SHI Jingzhao, CHEN Xinchang, ZHANG Feng. 3-parameter Weibull distribution parameter estimation based on matlab and GM（1,1）model ［J］. Jiangxi Science, 2010, 28(3): 291-294.
［13］刘程程, 杨力. PCA-SVR在煤层瓦斯含量预测中的应用［J］. 中国安全生产科学技术, 2012, 8(7): 78-82. LIU Chengcheng, YANG Li. Application of PCA-SVR on gas content predicting in coal seam ［J］. Journal of Safety Science and Technology, 2012, 8(7): 78-82.
［14］VAPNIK V N. The Nature of Statistical Learning Theory ［M］. New York: Sprinter, 1999.
［15］尹浩霖, 王达梦, 马志勇, 等. 支持向量回归参数估计在风电机组故障模式分析中的应用［J］. 机械科学与技术, 2018, 37(11):1755-1761. YIN Haolin, WANG Dameng, MA Zhiyong, et al. Application of support vector regression parameter estimation to fault mode analysis in wind turbines ［J］. Mechanical Science and Technology for Aerospace Engineering, 2018, 37(11): 1755-1761.
［16］奉国和. SVM分类核函数及参数选择比较［J］. 计算机工程与应用, 2011, 47(3): 123-124. FENG Guohe. Parameter optimizing for Support Vector Machines classification ［J］. Computer Engineering and Applications, 2011, 47(3): 123-124.
［17］张新锋, 赵彦, 王生昌, 等. 基于支持向量机的小样本威布尔可靠性分析［J］. 机械科学与技术, 2012, 31(8): 1359-1362，1368. ZHANG Xinfeng, ZHAO Yan, WANG Shengchang, et al. Weibull reliability analysis in small samples based on SVM ［J］. Mechanical Science and Technology for Aerospace Engineering, 2012, 31(8): 1359-1362，1368.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期： 2018-11-07
基金项目： 陕西省自然科学基础研究计划一般项目（青年）（2018JQ5131）
作者简介： 赵江平，硕士，副教授，主要研究方向为工业灾害防治理论及技术、工业防毒与职业卫生等。
通信作者： 丁洁，硕士研究生，主要研究方向为安全评价与风险评估。
更新日期/Last Update: 2019-01-31