Abstract: A new method for predicting the bearing capacity of high-rise building foundation under complex geological conditions is proposed to reduce the prediction error. Support vector machine algorithm was introduced in this prediction method, the relaxation coefficient is incorporated, and genetic algorithm was used to optimize the support vector machine, the foundation bearing capacity prediction model was constructed, and the implementation process of the prediction method was designed to realize the foundation bearing capacity prediction of high-rise buildings. The experimental results show that the settlement prediction error of the proposed bearing capacity prediction method is less than 2%, and the absolute error is less than 0.0005mm. This method effectively reduces the prediction error of the bearing capacity of high-rise building foundations and has certain feasibility.

Key words: complex geology, high rise building, foundation bearing capacity, bearing capacity prediction, prediction method

摘要： 复杂地质条件下地基沉降预测存在预测误差大的问题。为降低预测误差,文中提出一种新的复杂地质条件下高层建筑地基承载力预测方法。该预测方法引入支持向量机算法,融入松弛系数,通过遗传算法优化支持向量机,构建地基承载力预测模型,并且设计了预测方法实现流程,实现高层建筑地基承载力预测。结果表明:该预测方法的沉降预测误差低于2%,绝对误差低于0.0005mm。该方法有效降低了高层建筑地基承载力预测误差,具有一定的可行性。

关键词: 复杂地质, 高层建筑, 地基承载力, 承载力预测, 预测方法