非线性位移时间序列预测的进化-支持向量机方法及应用

Study and application of genetic-support vector machine for nonlinear displacement time series forecasting

摘要: 提出了一种新的岩土结构位移预测的进化支持向量机方法,用遗传算法来搜索支持向量机的参数和核函数,避免了人为选择参数的盲目性,同时提高了支持向量机的推广预测能力;利用这种非线性智能预测方法,滚动预测施工位移变形量,以便及时调整和优化施工步序,维护岩土结构的稳定性。将该方法用于卧龙寺边坡变形、三峡永船闸边坡变形预测,结果表明,该方法具有科学可靠、实时性的优点,具有广泛的应用前景。

Abstract: The geneticsupport vector machine method was used to forecast the nonlinear displacement in geotechnical engineering.It is showed this method can escape from the blindness of manmade choice of the parameter and kernel function of support vector machine.It enhances the efficiency and the capability of forecasting.The engineering case studies indicate that it is scientific and there is an extensive prospect for this real time forecasting.