|本期目录/Table of Contents|

[1]崔益虎,张庆武.基于支持向量机的泄爆压力峰值预测模型[J].南京工业大学学报(自然科学版),2014,36(05):107-111.[doi:10.3969/j.issn.1671-7627.2014.05.019]
 CUI Yihu,ZHANG Qingwu.Prediction model of venting peak pressure in vessel based on support vector machine[J].Journal of NANJING TECH UNIVERSITY(NATURAL SCIENCE EDITION),2014,36(05):107-111.[doi:10.3969/j.issn.1671-7627.2014.05.019]
点击复制

基于支持向量机的泄爆压力峰值预测模型()
分享到:

《南京工业大学学报(自然科学版)》[ISSN:1671-7627/CN:32-1670/N]

卷:
36
期数:
2014年05期
页码:
107-111
栏目:
出版日期:
2014-09-30

文章信息/Info

Title:
Prediction model of venting peak pressure in vessel based on support vector machine
文章编号:
1671-7627(2014)05-0107-05
作者:
崔益虎张庆武
南京工业大学 城市建设与安全工程学院,江苏 南京 210009
Author(s):
CUI YihuZHANG Qingwu
College of Urban Construction and Safety Engineering,Nanjing Tech University,Nanjing 210009,China
关键词:
泄爆压力峰值 支持向量机 预测模型
Keywords:
venting peak pressure support vector machine prediction model
分类号:
TQ086;X932
DOI:
10.3969/j.issn.1671-7627.2014.05.019
文献标志码:
A
摘要:
在现有的气体爆炸泄爆实验及理论研究的基础上,归纳总结泄爆过程中影响容器内压力峰值的主要因素,将这些因素作为输入,对压力峰值与各因素之间的内在非线性关系进行模拟,提出一种基于支持向量机的容器内气体爆炸泄爆压力峰值预测方法。对模型的有效性及预测性能进行验证,表明模型预测的结果与实验值基本一致; 将模型的预测性能与现有的经验、半经验公式以及泄爆设计准则进行对比,表明建立的模型具有较高的准确性,为容器泄爆设计提供了一种新的途径。
Abstract:
Based on the experimental and theoretical research on gas explosion venting,major factors influencing on the peak pressure of vented vessel were summarized. A prediction method of pressure peak for a vented explosion based on the support vector machine(SVM)was proposed. By using the major factors as inputs and training the inner non-linear relationship between the pressure peak and each factor,validity and predictability of the SVM model were checked by the prediction values and experimental ones.Compared with the empirical formula and semi-empirical formula, the SVM-based model had higher accuracy,which would provide a new way for the design of gas explosion venting.

参考文献/References:

[1] 喻源,蒋军成,张庆武,等.球形容器泄爆收容的实验分析[J].解放军理工大学学报,2012,13(5):544-548.
[2] Razus D M,Krause U.Comparison of empirical and sem-iempirical calculation methods for venting of gas explosions[J].Fire Safety Journal,2001,36:1-23.
[3] American National Standards Institute.Standard on explosion protection by deflagration venting(NFPA 68)[S].Quincy:National Fire Protection Association,2007.
[4] Verein Deutscher Ingenieure.Pressure venting of dust explosions:VDI 3673.Part l[S].Dusseldorf:Verien Deutscher Ingenieure,1995.
[5] 杨洪,古世甫,崔明东,等.基于遗传优化的最小二乘支持向量机风电场风速短期预测[J].电力系统保护与控制,2011,39(11):44-48.
[6] Vapnik V N.The Nature of Statistical Learning Theory[M].New York:Springer,1995.
[7] 钱渊,宋军,傅柯.基于支持向量机补偿的灰色模型网络流量预测[J].探测与控制学报,2012,34(1):69-79.
[8] 杜颖,卢继平,李青,等.基于最小二乘支持向量机的风电场短期风速预测[J].电网技术,2008,32(15):62-66.
[9] 潘勇,蒋军成,王睿.基于定量结构性质相关性的烃类物质爆炸下限预测[J].爆炸与冲击,2010,30(3):288-294.
[10] 谭鹏,曹平.基于灰色关联支持向量机的地表沉降预测[J].中南大学学报:自然科学版,2012,43(2):632-637.
[11] 杨斌,匡立春,孙中春.一种用于测井油气层综合识别的支持向量机方法[J].测井技术,2005,29(6):511-514.

相似文献/References:

[1]刘济宁,吕凤兰,石利利,等.芳香族化合物的快速生物降解性QSBR研究[J].南京工业大学学报(自然科学版),2012,34(05):38.
 LIU Jining,LÜ,Fenglan,et al.QSBR on ready biodegradability of aromatic compounds[J].Journal of NANJING TECH UNIVERSITY(NATURAL SCIENCE EDITION),2012,34(05):38.
[2]陆超,陈捷,洪荣晶,等.基于粒子群优化支持向量机的回转支承寿命状态识别[J].南京工业大学学报(自然科学版),2016,38(01):56.[doi:10.3969/j.issn.1671-7627.2016.01.010]
 LU Chao,CHEN Jie,HONG Rongjing,et al.Slewing bearing life state recognition based on support vector machine optimized by particle swarm[J].Journal of NANJING TECH UNIVERSITY(NATURAL SCIENCE EDITION),2016,38(05):56.[doi:10.3969/j.issn.1671-7627.2016.01.010]

备注/Memo

备注/Memo:
收稿日期:2013-09-05
基金项目:国家自然科学基金(20976081,50904037); 江苏省高校自然科学基金(12KJB620001)
作者简介:崔益虎(1963—),男,江苏海安人,博士,主要研究方向为气体爆炸及其防治措施,E-mail:yihucui@163.com..
更新日期/Last Update: 2014-09-20