非线性位移时间序列分析模型的进化识别

Evolutionary Identification of Analysis Model for Nonlinear Displacement Time Series

引入进化算法的全局优化思想,结合时间序列分析的基本理论,提出了一种新的岩土结构变形非线性动力学演化特征的进化识别算法·设计了能自动确定输入时步长度以及非线性动力学模型结构和参数的分步进化方案,对非线性时间序列分析模型的结构和参数进行全局最优搜索·将该方法用于三峡永久船闸高边坡开挖变形的预测分析,取得了满意的效果,提供了一个有效的岩土工程设计与施工的分析工具·

Combining the global optimal techniques of evolutionary algorithm with the elementary theory of time series analysis, a new evolutionary method was proposed to identify the nonlinear dynamically evolving behavior of the deformation of geotechnical structures. A multi-rank evolutionary scheme,which can automatically specify the number of input steps and the structure and parameters of the nonlinear dynamic model was therefore designed to search the global optimal structure and parameters of the nonlinear time series model. A successful application of the method proposed to the prediction analysis of displacement of the high slope relating to the permanent shiplock in the Three Gorges Project showed its validity and advantages available to provide an efficient tool for the design and construction of geotechnical engineering.