基于相空间重构的FOA-GLSSVM深基坑变形预测模型研究

针对LSSVM模型参数选择的随机性与单一变量序列高维度重构参数选择的困难性，将相空间重构理论、果蝇优化算法引入LSSVM模型中，建立基于相空间重构的FOA-GLSSVM变形预测模型。为了验证提出模型的有效性与可靠性，结合具体工程实例与GLSSVM、支持向量机模型及最小二乘支持向量机模型进行对比研究。结果表明，提出的模型精度更好、稳定性更强。

Research on Deformation Prediction Model of FOA-GLSSVM Deep Foundation Pit Based on Phase Space Reconstruction

This study is concerned with the difficulty of parameter selection in the LSSVM model and the selection of parameters for high dimensional reconstruction of single variable sequences. To this end, we introduce the phase space reconstruction theory, and fruit fly algorithm into the LSSVM model. The deformation prediction model of phase space reconstruction based on FOA-GLSSVM is established. In order to validate the effectiveness and reliability of the proposed model, we compare practical examples and the GLSSVM model, least square support vector machine model and support vector machine model. The experimental results show that the proposed model is more accurate and stable.