基于随机森林算法的高层建筑机械拆除方法判断  

DEMOLITION METHODS OF HIGH-RISE BUILDINGS BASED ON RANDOM FOREST ALGORITHM

作　　者：王勃[1,2] 崔洋 董丽欣 WANG Bo;CUI Yang;DONG Lixin(School of Civil Engineering,Jilin Jianzhu University,Changchun 130118,China;Jilin Structural and Earthquake Resistance Technology Innovation Center,Changchun 130118,China)

机构地区：[1]吉林建筑大学土木工程学院,长春130118 [2]吉林省结构与抗震科技创新中心,长春130118

出　　处：《低温建筑技术》2020年第12期40-42,46,共4页Low Temperature Architecture Technology

基　　金：国家重点研发计划项目(2017YFC0806100);国家自然科学基金项目(51178206);吉林省高校“十三五”科研规划项目(JJKH20170253KJ)。

摘　　要：为了对高层建筑5种机械拆除方法的可行性进行判断,运用随机森林算法,以工程实例为样本在软件Matlab中建立5个分类模型。将随机森林模型与BP神经网络模型和CART决策树模型进行对比分析,综合考虑正确率和模型运行时间,结果表明随机森林模型正确率最高且运行时间短,证明了此方法是合理的,为高层建筑拆除工程应用提供理论依据和参考。In order to investigate the feasibility of five methods for mechanical demolition of high-rise buildings,five classification models were presented using random forest algorithm on Matlab software platform with engineering examples.Furthermore,forest algorithm model,BP neural network model,and CART decision tree model were compared,considering the correct rate and the running time of the models.The result shows that the random forest model has the highest accuracy and short running time.Moreover,the method is reasonable and provides the theoretical basis for demolishing engineering of high-rise buildings.

关 键 词：机械拆除 随机森林算法 拆除方法判断 

分 类 号：TU746.5[建筑科学—建筑技术科学]