基于SVM的EPC项目安全风险评价研究

Research on Safety Risk Assessment of EPC Project Based on SVM

为准确、有效地对EPC工程项目安全风险进行评价,降低工程事故发生率,应用支持向量机(SVM)算法评价EPC项目安全风险。首先,根据EPC工程总承包模式的特点及相关文献、资料定性分析EPC项目设计、采购及施工阶段安全风险因素,建立EPC项目安全风险评价指标体系;其次,将SVM算法运用于安全风险评价,构建基于SVM的EPC项目安全风险评价模型;最后,选取武汉市的20个典型EPC项目,利用所建立的SVM模型对其进行安全风险评价。结果显示预测准确度为87.5%,模型预测效果较好。

In order to evaluate the safety risks of EPC project accurately and effectively and reduce the incidence of engineering accidents,support vector machine(SVM)algorithm is applied to evaluate the safety risk of EPC project.Firstly,according to the characteristics of EPC project general contracting mode and related literature,qualitative analysis of EPC project design,procurement and construction stage safety risk factors,the establishment of EPC project safety risk evaluation index system.Secondly,the SVM algorithm is applied to the security risk evaluation,and the security risk evaluation model of EPC project based on SVM is constructed.Finally,20 typical EPC projects in Wuhan city were selected and the established SVM model was used to evaluate their security risks.The results showed that the prediction accuracy was 87.5%,and the prediction effect of the model was good.