基于随机森林算法的现代建筑工程施工过程监理效果影响因素分析

Analysis of Influencing Factors of Supervision Effect in Modern Construction Process Based on Random Forest Algorithm

文中以某现代建筑工程为背景,结合监理特点,选择施工过程质量监理、安全监理、进度监理以及投资监理作为监理效果影响因子,并提出假设。以监理效果作为因变量,以选择的影响因子作为自变量,利用随机森林算法建立分析模型,并对模型开展训练,通过模型迭代计算,对提出的假设进行验证,并确定自变量对因变量的重要性。经模型验证,监理效果主要受施工过程质量监理、安全监理、进度监理以及投资监理影响,其中,安全监理对整个施工过程监理效果影响最大。

With a modern construction project as the engineering background,this paper combined with the construction process supervision characteristics,the construction process quality supervision,safety supervision,progress supervision and investment supervision as the supervision effect factors,and put forward the hypothesis.With the supervision effect as the dependent variable and the selected influence factor as the independent variable,the random forest algorithm was used to establish the analysis model,and the model was trained.Through the model iterative calculation,the hypothesis was validated,and the importance of the independent variable to the dependent variable was determined.The model verifies that the supervision effect is mainly affected by the quality supervision,safety supervision,progress supervision and investment supervision in the construction process,among which the safety supervision has the greatest influence on the supervision effect in the whole construction process.