基于支持向量机和Bootstrap的粮仓建筑气密性区间预测方法

Method for interval prediction of granary airtightness based on Support Vector Machine and Bootstrap

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 show that the method mentioned in the paper has good performance.In a word,the paper provides a new tool for improving the design schemes of granaries.