基于MAPSO-LSSVM模型的基坑开挖对周围建筑物沉降预测研究

Prediction of Surrounding Building Settlement Based on MAPSO-LSSVM Model

为了快速准确的预测基坑开挖对周围建筑物沉降的影响,本文提出一种结合多智能体粒子寻求LSSVM(最小二乘支持向量机)模型参数的算法,提高了LSSVM算法的预测精度.采用该算法对昆明市某基坑开挖过程中周围建筑物的沉降进行预测,并与其他预测方法进行对比,结果表明该算法具有收敛速度快、预测精度高等特点.

This research is carried out in order to quickly and accurately predict the influence of excavation on the surrounding buildings. An algorithm based on multi -agent particle swarm is proposed to find the parameters of the LSSVM （LSSVM） model, which improves the prediction accuracy of the LSSVM algorithm. The algorithm is used to predict the settlement of the surrounding buildings during the excavation of a foundation pit in Kunming, and the results are then compared with other prediction methods. The results show that the algorithm has the characteristics of fast convergence and high precision.