基于极限学习机的新型挡土墙安全性预测研究  

Safety Prediction Research of New Assembled Retaining Wall Based on Extreme Learning Machine

作　　者：冷慧琳 李小五[2] 王列健 Leng Huiling;Li Xiaowu;Wang Liejian(Chongqing Water Conservancy and Electric Power construction survey,design and Research Institute Go.Ltd.,Chongqing 401120;China Water Resources Pearl River Planning Surveying&Designing Co.Ltd.,Guangzhou,Guangdong,510000)

机构地区：[1]重庆市水利电力建筑勘测设计研究院有限公司,重庆404100 [2]中水珠江规划勘测设计有限公司,广东广州510610

出　　处：《江西建材》2022年第4期100-101,108,共3页Jiangxi Building Materials

摘　　要：挡土墙安全性能是水利工程设计和运行环节都需关注的重点问题,常规挡土墙设计存在过于保守的缺陷。墙体形态、工程材料、地基承载能力、墙后填土力学参数等对挡土墙整体安全性能影响错综复杂。文中以仰斜式新型挡土墙为例,基于前人计算的挡土墙相关安全系数结果,采用优化极限学习机,预测了相关安全系数。结果表明,优化后的极限学习机能够较好地反映多种影响因素与挡土墙安全性能之间的映射关系,表现出较好的泛化性,可为快速精确进行挡土墙安全性能评估提供参考。The safety performance of the retaining wall is a hot issue that needs to be paid attention to in the design and operation of hydraulic engineering. The retaining wall design under the conventional design ideas has the defect of being too conservative. Wall shape,engineering materials, foundation bearing capacity, and mechanical parameters of backfilling have complicated effects on the overall safety performance of retaining walls. In this paper, taking the new inclined type retaining wall as an example, based on the results of the relevant safety factor of the retaining wall calculated by the predecessors, the optimized extreme learning machine is used to predict the relevant safety factor. The results show that the optimized extreme learning machine can better reflect the mapping relationship between various influencing factors and the safety performance of the retaining wall, and shows good generalization, which can be used for the rapid and accurate evaluation of the safety performance of the retaining wall. for reference.

关 键 词：挡土墙 安全性 机器学习 极限学习机 

分 类 号：TU476[建筑科学—结构工程]