基于多分类GA-SVM的装配式建筑吊装作业安全预警分析  

Safety warning analysis of prefabricated building hoisting operation based on multi-classification

作　　者：黄莺[1] 杜树 郭俊浩 熊文文 HUANG Ying;DU Shu;GUO Junhao;XIONG Wenwen(School of Civil Engineering,Xi'an University of Architecture and Technology,Xi'an Shaanxi 710055,China;不详)

机构地区：[1]西安建筑科技大学土木工程学院,陕西西安710055 [2]西安建筑科技大学资源工程学院,陕西西安710055 [3]上海建科工程咨询有限公司,上海200032

出　　处：《工业安全与环保》2023年第8期35-39,共5页Industrial Safety and Environmental Protection

基　　金：陕西省自然科学基础研究基金(2020JM-494)。

摘　　要：吊装作业是装配式建筑施工极为重要的一环,其在施工过程中的安全问题不容忽视。为了对装配式建筑吊装作业安全预警进行研究,以“4M”理论为出发点,提出一种基于GA-SVM的吊装作业安全预警模型,将遗传算法与支持向量机融合,提升模型的分类准确率。将支持向量机的二分类问题拓展到四分类问题上,并以实际工程案例加以验证。结果表明:通过GA与SVM结合建立的模型精度较好,实验预测结果与实际结果较为吻合,可以为装配式建筑施工的安全管理提供可靠的决策支持。Lifting operation is a very important part of assembly building construction,its safety problem in the con-struction process can not be ignored.In order to study the safety early warning of assembly building lifting operation,this paper,taking"4M"theory as the starting point,proposes a safety early warning model of lifting operation based on GA-SVM,and integrates genetic algorithm and support vector machine to improve the classification accuracy of the model.The binary classification problem of support vector machine is extended to four classification problem and verified by a practical engineering case.The results show that the model established by combining GA and SVM has good accuracy,and the experimental prediction results are in good agreement with the actual results,which can provide reliable decision support for the safety management of prefabricated building construction.

关 键 词：支持向量机 建筑施工 安全预警 装配式建筑 多分类问题 

分 类 号：TU741[建筑科学—建筑技术科学] TU758.15