基于最小二乘支持向量机回归的单桩竖向极限承载力预测

Prediction model of ultimate vertical bearing capacity of single pile based on least squares support vector machines

基于单桩载荷试验数据,采用最小二乘支持向量机(LSSVM)回归的方法,建立了单桩竖向极限承载力的预测模型.利用文献中桩的载荷试验数据来训练LSSVM模型,并确定了模型参数.研究结果表明,同常用的BP网络相比,LSSVM预测模型具有学习速度快、预测性能较好、选择参数少等优点,是一种有效的预测单桩极限承载力的方法.

Prediction model of ultimate vertical bearing capacity of single pile was established based on single pile loading test data using least squares support vector machines （LSSVM） regression. The LSSVM model was trained with the pile loading test data from the references, and the parameters of the model were selected. The results show that the LSSVM model approach is better than classical back-propagation （BP） neural network in terms of higher computation speed, less forecast errors, and less selective parameters. It is an effective method to predict ultimate vertical bearing capacity of single pile.