Sun Changshuai, Yu Tianwen, Li Min, Wei Huanwei, Tan Fang
Shandong Electric Power Engineering Consulting Institute Corp., Ltd, Jinan, 250013, China.
School of Civil Engineering, Shandong Jianzhu University, Jinan, 250101, China.
Sci Rep. 2024 Mar 1;14(1):5067. doi: 10.1038/s41598-024-55236-w.
By collecting a large amount of data from various preloading engineering projects, a settlement prediction database was established including up to 15 feature parameters, such as final measured time, magnitude of surcharge loading, porosity ratio, internal friction angle, and others. Furthermore, a settlement prediction model of soft foundation based on random forest (RF) model was also developed. To enhance the accuracy of settlement prediction, the improved sparrow search algorithm (ISSA), which incorporates several enhancements such as the use of Logistic-tent chaotic mapping, adaptive nonlinear inertia-decreasing weight parameters, and Levy flight strategy, was proposed to optimize the hyperparameters of the RF model. The optimization results of various algorithms on benchmark functions revealed that the ISSA algorithm excelled in terms of accuracy and stability when compared to conventional algorithms such as particle swarm optimization and butterfly optimization. The ISSA-RF settlement prediction model was subsequently constructed and applied to practical projects. The results demonstrated that the ISSA-RF model exhibited superior prediction accuracy and applicability compared to the RF model. It can therefore provide valuable guidance for the planning and implementation of preloading engineering projects.
通过收集大量不同的预压工程项目数据，建立了一个沉降预测数据库，其中包含多达15个特征参数，如最终测量时间、超载量、孔隙比、内摩擦角等。此外，还开发了基于随机森林（RF）模型的软土地基沉降预测模型。为提高沉降预测的准确性，提出了改进的麻雀搜索算法（ISSA），该算法采用了Logistic-帐篷混沌映射、自适应非线性惯性递减权重参数和Levy飞行策略等多种改进方法，用于优化RF模型的超参数。各种算法在基准函数上的优化结果表明，与粒子群优化和蝴蝶优化等传统算法相比，ISSA算法在准确性和稳定性方面表现出色。随后构建了ISSA-RF沉降预测模型并应用于实际工程。结果表明，与RF模型相比，ISSA-RF模型具有更高的预测精度和适用性。因此，它可为预压工程项目的规划和实施提供有价值的指导。
