以探讨边坡变形性质及混沌预测可行性为目的,基于混沌理论利用相空间重构技术对其变形时间序列进行混沌特征判定,试验显示变形系统具有混沌特性,可用混沌相关理论进行研究;基于混沌相空间重构技术,笔者构建了多种混沌预测模型进行混沌预计研究,分析各类模型的工程实际应用效果;针对单次监测时序预测精度较低的问题,提出累加时序预测方案,训练结果显示,短期预测精度变形累计值基本控制在5%以内,高程值预测相对误差均低于1%,预测精度较高,可以用于工程实际。
To explore the deformation character of slope and the feasibility to predict it with chaotic theory, a test of chaotic character judgment was conducted on the deformation time sequence of slopes by using phase space reconstruction theory. The results show that the deformation system of slope has chaotic traits and can be studied with chaotic theory. Several chaotic prediction models were built on the basis of phase space reconstruction theory, and the application effect of these models in engineering was analyzed. Aiming at the problem of low precision in single monitoring, a prediction method of sequence accumulation was proposed. The training result shows that the accumulative value of short-term prediction precision can be controlled within 5%, and the relative prediction error of height value is lower than 1%. It is concluded that this method has a high precision of prediction and can be applied to engineering.