In order to solve the problem of quality control of subgrade compaction detection in road engineering construction,the influence of key material parameters on subgrade compaction is studied,and an analysis and prediction model based on ensemble learning algorithm is proposed.The results show that in the matching analysis of subgrade material parameters and the change trend of compaction,the wet density has the most significant influence on the compaction of subgrade.At the same time,among the three prediction models of deep forest,XGBoost and random forest,the deep forest model is the most accurate,and the goodness of fit R2 can reach 0.992 8,showing the high-precision prediction function of subgrade compaction.Based on a series of data analysis,this paper aims to help relevant enterprises better carry out the dynamic detection of subgrade compaction quality,and provide a decision-making basis for the optimization of the current road construction quality improvement work.
关键词
路基工程/物联网检测/材料关键参数/深度森林预测模型
Key words
subgrade works/IoT detection/material key parameters/deep forest prediction model
维普
万方数据