基于支持向量机和Bootstrap的粮仓建筑气密性区间预测方法
|
摘要
粮仓建筑的气密性对于储粮安全具有重要影响,本研究的目的在于提供一种可以用于在粮仓设计阶段进行粮仓气密性预测的方法,以方便设计人员根据粮仓设计方案的气密性预测结果优化设计,确保粮仓建成后能够符合气密性要求。本研究采用的样本数据集合包括已建成粮仓的建筑特征变量和气密性检测结果,把该样本集合随机划分为训练集合和测试集合,利用训练数据集合训练支持向量机回归模型,并采用Bootstrap方法进行训练样本抽样,从而实现对粮仓气密性的区间预测。测试结果表明该方法具有良好的性能,为改进粮仓设计方案提供了一种新工具。
Airtightness of granary has an important effect on grain storage safety,the aim of the paper is to provide a method which can be used in the prediction of the granary airtightness during the design stage. According to the prediction of granary airtightness,designers can improve the designs and make sure that the granaries in design will meet the airtightness requirements after they are built. In the paper,data including the architectural characteristic variables and airtightness test results of built granaries are taken as the sample data set,and the sample data set is randomly divided into the training set and the testing set. The training set is employed to train the Support Vector Machine regression model,and the Bootstrap method is adopted to sample with replacement so as to acquire the interval prediction of granary airtightness. The test results showthat the method mentioned in the paper has good performance. In a word,the paper provides a newtool for improving the design schemes of granaries.
Airtightness of granary has an important effect on grain storage safety,the aim of the paper is to provide a method which can be used in the prediction of the granary airtightness during the design stage. According to the prediction of granary airtightness,designers can improve the designs and make sure that the granaries in design will meet the airtightness requirements after they are built. In the paper,data including the architectural characteristic variables and airtightness test results of built granaries are taken as the sample data set,and the sample data set is randomly divided into the training set and the testing set. The training set is employed to train the Support Vector Machine regression model,and the Bootstrap method is adopted to sample with replacement so as to acquire the interval prediction of granary airtightness. The test results showthat the method mentioned in the paper has good performance. In a word,the paper provides a newtool for improving the design schemes of granaries.
引文
[1]中华人民共和国国家质量监督检验检疫总局. GB/T25229-2010粮油储藏平房仓气密性要求[S].北京:中国标准出版社,2010.
[2]李宝升,李岩峰,凌才青,等.气调储粮技术的发展与应用研究[J].粮食加工,2015,40(5):71-74,77.
[3]陈旭,张峻岭.粮仓气密性检测对储粮安全的重要性分析[J].粮油仓储科技通讯,2017,33(6):30-33.
[4]张峻岭,陈旭,孙慧男.论粮仓气密性对储粮安全的重要性[J].现代食品,2017(18):22-26.
[5]张来林,李超彬,赵英杰.粮仓的气密性测试与气密改造[J].粮食储藏,2003,32(4):15-18.
[6]刘佳,戴春景,许隽,等.粮食平房仓气密性影响因素及改进措施[J].粮食与食品工业,2010,17(4):33-35.
[7]张来林,赵英杰,狄彦芳,等.粮食仓房气密性测试与CM系列仓用密封门窗应用报告[J].粮食储藏,2000,29(6):18-24.
[8]陶金亚,张来林,黄浙文,等.粮食仓房的气密性分析[J].现代食品,2016(16):26-30.
[9]王薇.粮食仓房的保温隔热、气密性技术措施研究及应用[D].天津:天津大学,2009.
[10]党向盈,姜代红.神经网络结合遗传算法在建筑优化设计中的应用[J].徐州工程学院学报(自然科学版),2017,32(2):66-71.
[11]孙国明,杨佳欣.神经网络在民用建筑设计工程中的应用[J].工程建设与设计,2012(10):138-140.
[12]赖鑫生.神经网络结合遗传算法优化应用[J].贵州大学学报(自然科学版),2004,21(2):179-184.
[13]李建,陈烈,茅林明.支持向量机在建筑能耗预测中的应用[J].建筑节能,2014,42(12):77-80.
[14]李杰.改进粒子群算法优化支持向量机的工程造价预测[J].计算机系统应用,2016,25(6):202-206.
[15]ZHOU Ying,SU Wanjun,DING Lieyun,et al. Predicting safety risks in deep foundation pits in subw ay infrastructure projects:Support Vector M achine approach[J]. Journal of Computing in Civil Engineering,2017,31(5):04017052.
[16]SAMUI P. Support vector machine applied to settlement of shallow foundations on cohesionless soils[J]. Computers and Geotechnics,2008,35(3):419-427.
[17]CHANG C C,LIN C J. LIBSVM:A library for support vector machines[J]. ACM Transactions on Internet Systems and Technology,2011,2:27:1-27:27.
[18]谢益辉,朱钰. Bootstrap方法的历史发展和前沿研究[J].统计与信息论坛,2008,23(2):90-96.
[19]赵玉,祁春节.大宗农产品价格风险评估—基于小波神经网络-Bootstrap方法的实证研究[J].技术经济,2014,33(3):75-79.
[20]陈娇娜,张翔,张生瑞.高速公路行程时间Bootstrap-KNN区间预测分析与实证[J].控制与决策,2018,33(11):2080-2086.
[21]NEGNEVITSKY M. Artificial intelligence:A guide to intelligent systems[M]. 3rded. Harlow:Pearson Education Limited,2001.
[22]EFRON B R,TIBSHIRANI J. An introduction to the Bootstrap[M]. London:Chapman and Hall/CRC,1993.
[23]KHOSRAVI A,NAHAVANDI S,SRINIVASAN D, et al.Constructing optimal prediction intervals by using neural netw orks and bootstrap method[J]. IEEE Transactions on Neural Netw orks and Learning Systems,2015,26(8):1810-1815.
[2]李宝升,李岩峰,凌才青,等.气调储粮技术的发展与应用研究[J].粮食加工,2015,40(5):71-74,77.
[3]陈旭,张峻岭.粮仓气密性检测对储粮安全的重要性分析[J].粮油仓储科技通讯,2017,33(6):30-33.
[4]张峻岭,陈旭,孙慧男.论粮仓气密性对储粮安全的重要性[J].现代食品,2017(18):22-26.
[5]张来林,李超彬,赵英杰.粮仓的气密性测试与气密改造[J].粮食储藏,2003,32(4):15-18.
[6]刘佳,戴春景,许隽,等.粮食平房仓气密性影响因素及改进措施[J].粮食与食品工业,2010,17(4):33-35.
[7]张来林,赵英杰,狄彦芳,等.粮食仓房气密性测试与CM系列仓用密封门窗应用报告[J].粮食储藏,2000,29(6):18-24.
[8]陶金亚,张来林,黄浙文,等.粮食仓房的气密性分析[J].现代食品,2016(16):26-30.
[9]王薇.粮食仓房的保温隔热、气密性技术措施研究及应用[D].天津:天津大学,2009.
[10]党向盈,姜代红.神经网络结合遗传算法在建筑优化设计中的应用[J].徐州工程学院学报(自然科学版),2017,32(2):66-71.
[11]孙国明,杨佳欣.神经网络在民用建筑设计工程中的应用[J].工程建设与设计,2012(10):138-140.
[12]赖鑫生.神经网络结合遗传算法优化应用[J].贵州大学学报(自然科学版),2004,21(2):179-184.
[13]李建,陈烈,茅林明.支持向量机在建筑能耗预测中的应用[J].建筑节能,2014,42(12):77-80.
[14]李杰.改进粒子群算法优化支持向量机的工程造价预测[J].计算机系统应用,2016,25(6):202-206.
[15]ZHOU Ying,SU Wanjun,DING Lieyun,et al. Predicting safety risks in deep foundation pits in subw ay infrastructure projects:Support Vector M achine approach[J]. Journal of Computing in Civil Engineering,2017,31(5):04017052.
[16]SAMUI P. Support vector machine applied to settlement of shallow foundations on cohesionless soils[J]. Computers and Geotechnics,2008,35(3):419-427.
[17]CHANG C C,LIN C J. LIBSVM:A library for support vector machines[J]. ACM Transactions on Internet Systems and Technology,2011,2:27:1-27:27.
[18]谢益辉,朱钰. Bootstrap方法的历史发展和前沿研究[J].统计与信息论坛,2008,23(2):90-96.
[19]赵玉,祁春节.大宗农产品价格风险评估—基于小波神经网络-Bootstrap方法的实证研究[J].技术经济,2014,33(3):75-79.
[20]陈娇娜,张翔,张生瑞.高速公路行程时间Bootstrap-KNN区间预测分析与实证[J].控制与决策,2018,33(11):2080-2086.
[21]NEGNEVITSKY M. Artificial intelligence:A guide to intelligent systems[M]. 3rded. Harlow:Pearson Education Limited,2001.
[22]EFRON B R,TIBSHIRANI J. An introduction to the Bootstrap[M]. London:Chapman and Hall/CRC,1993.
[23]KHOSRAVI A,NAHAVANDI S,SRINIVASAN D, et al.Constructing optimal prediction intervals by using neural netw orks and bootstrap method[J]. IEEE Transactions on Neural Netw orks and Learning Systems,2015,26(8):1810-1815.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |