基于EO-LightGBM融合模型的边坡稳定性预测方法研究
STUDY ON SLOPE STABILITY PREDICTION METHOD BASED ON EO-LIGHTGBM FUSION MODEL
白龙发 1李保珠 1时鹏程1
作者信息
- 1. 昆明理工大学国土资源工程学院,昆明 650093
- 折叠
摘要
边坡稳定性预测是确保边坡工程安全、经济和环保的关键环节.通过一系列数据对边坡的稳定性状态进行预测,不仅避免了进行复杂的计算,还能更好地了解边坡的稳定情况.基于此,本文提出了一种基于EO-LightGBM模型的边坡稳定性预测方法,并通过学习边坡的重度、内聚力、摩擦角、边坡角、边坡高度、孔隙压力比这6个特征和稳定性状态之间的关系,实现对边坡稳定性的预测.此外,通过与其他模型的对比研究,验证了本文所提出的EO-LightGBM模型的可靠性.研究结果表明:使用EO优化后的LightGBM模型误判率更低,具有更高的准确性,可以更好地预测边坡的稳定性状态;同时也将为建立基于数据驱动的边坡稳定性智能决策控制平台提供参考.
Abstract
Slope stability prediction is a key link to ensure the safety,economy and environmental protection of slope engineering.Through a series of data,the stability state of the slope is predicted,which not only avoids complex calculations,but also better understands the stability of the slope.Based on this,this paper proposes a slope stability prediction method based on EO-LightGBM model,and realizes the prediction of slope stability by learning the relationship between the six characteristics of slope gravity,cohesion,friction angle,slope angle,slope height,pore pressure ratio and stability state.In addition,the reliability of the EO-LightGBM model proposed in this paper is verified by comparing with other models.On the surface of the research results,the LightGBM model optimized by EO has lower misjudgment rate and higher accuracy,which can better predict the stability state of the slope.At the same time,it will also provide a reference for the establishment of an intelligent decision-making control platform for slope stability based on data-driven.
关键词
边坡稳定性/融合模型/机器学习/智能预测/数据驱动Key words
slope stability/fusion model/machine learning/intelligent prediction/data-driven引用本文复制引用
出版年
2024
NETL
NSTL
万方数据