遗传门限自回归模型的改进及其应用  

Improvement of Threshold Auto-regressive Model Based on Genetic Algorithm and Its Application

作　　者：金光球[1] 汪莲[2] 王宗志[2] 徐金[2] 曹明宏[3] 

机构地区：[1]河海大学水利水电工程学院,南京210098 [2]合肥工业大学土木建筑工程学院,合肥230009 [3]安徽鸿路钢结构有限公司,合肥231131

出　　处：《长江科学院院报》2006年第2期31-34,共4页Journal of Changjiang River Scientific Research Institute

摘　　要：针对门限自回归模型在实际应用过程中预测效果差于拟合效果的情况,对门限自回归模型作了改进,即:在对时序x(i)拟合和预测时,AR式靠近i半个周期的观测值用门限自回归模型的拟合和预测的计算值代替;为了清晰直观地确定出延迟步数及门限区间AR模型的阶数,提出了通过绘制自相关系数图来确定。实例表明,该改进方法提高了遗传门限自回归模型的稳定性和实用性,模型在大坝安全位移监测预报中得到了成功的应用。Because fitted effect of threshold auto-regressive（TAR） model is sometimes better than its predicted effect, or predicted effect is bad, TAR is improved, i.e. , when time series x （ i ） are fitted and predicted, AR＇s observed values of half period besides i are replaced by calculated values of fit or forecasting of TAR model. By depicting the figure of auto correlation coefficients, it may ascertain clearly delayed paces and ranks of the autoregressive model of threshold sections. The result of an example shows its improvement can enhance stability and practicability of the model and application of TAR in security supervision forecast is effective and successful.

关 键 词：遗传算法 门限自回归模型 大坝 安全监测 

分 类 号：TV698.11[水利工程—水利水电工程]