摘要
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。
Based on the displacement sequence of slope,the stability of slope could be judged effectively by forecasting the displacement of slope in the future.After analyzing the advantages and disadvantages of grey forecasting methods and projection pursuit regression（PPR） method respectively;a new nonlinear forecasting model of grey projection pursuit regression（GPPR） is proposed.The new model not only developing the advantages of accumulation generation of the grey forecasting method,weakening the effect of stochastic-disturbing factors in original sequence and strengthening the regularity of data,but also using the quickly solving speed and the excellent characteristics of projection pursuit regression method for nonlinear relationship and avoiding the theoretical defects existing in the grey forecasting model.At the same time,the model is verified.At last,two engineering examples are given to testify the effectiveness of the grey projection pursuit regression forecasting method to predict displacements of two slopes.The results show that the new model has higher calculation precision,so as to provide a new way to predict displacements of slopes.
出处
《岩土力学》
EI
CAS
CSCD
北大核心
2011年第6期1808-1812,共5页
Rock and Soil Mechanics
基金
安徽省教育厅自然科学基金重点项目资助(No.KJ2008A143)
关键词
边坡位移
灰色理论
投影寻踪回归方法
时间序列
非线性
slope displacement
grey theory
projection pursuit regression
time sequence
nonlinearity
