论文部分内容阅读
通过边坡现场监测位移序列来预测未来时间边坡的位移,可以有效地评价和判断边坡的稳定性。多种非线性分析方法的组合可以有效提高预测精度,将灰色理论与投影寻踪回归各自的优缺点的基础上,提出了将二者相结合的一种新的预测模型——时序投影寻踪回归模型。新模型既发挥了灰色预测方法中“累加生成”的优点,弱化了原始序列中随机扰动因素的影响,增强了数据的规律性,又充分利用了投影寻踪回归方法易于描述非线性关系的优良特性,避免了灰色预测方法及模型存在的理论缺陷。同时,对模型的可靠性进行了验证。将文中提出的时序投影寻踪回归方法应用到2个工程实例,研究结果表明该模型预测值与实测值吻合较好,具有较高的精度,可为边坡位移的预测提供一条新的途径。
By predicting the slope displacement in the future by monitoring the displacement sequence on the slope, the stability of the slope can be effectively evaluated and judged. The combination of multiple nonlinear analysis methods can effectively improve the prediction accuracy. Based on the respective advantages and disadvantages of gray theory and projection pursuit, a new predictive model combining temporal projection pursuit Regression model. The new model not only displays the advantages of “accumulation generation ” in the gray prediction method, but also weakens the influence of random perturbation factors in the original sequence, enhances the regularity of the data and makes full use of the projection pursuit regression method to easily describe the nonlinear relationship , Which avoids the theoretical flaws of the gray prediction method and model. At the same time, the reliability of the model is verified. The time series projection pursuit regression method proposed in this paper is applied to two engineering examples. The results show that the predicted value of the model is in good agreement with the measured value and has high precision, which can provide a new approach for the prediction of slope displacement.