基于遗传算法的双线性模型在大坝安全监测预报中的应用

Application of bilinear time series model based on genetic algorithms in dam security monitoring forecast

文章提出了实用自相关系数图确定双线性模型的自回归项,应用了基于遗传算法的一套建模方法。通过实例表明,由于双线性模型实际拟合和预测过程中产生的残差信息进行反馈矫正,保证了模型高的拟合精度和稳健的预测性能,与门限自回归模型比较,双线性模型比门限自回归模型具有更好的预测精度。

The auto correlation coefficients figure is suggested to ascertain auto regressive items of bilinear time series model（BM）. A scheme based on genetic algorithms is adopted to deduce the BM. Calculation of the example shows that the precision of the model is good and its forecast capability is stable because the BM uses the feedback information of prediction residual errors in the course of fitting and forecasting. The forecast precision of the BM is better in comparison with the threshold autoregressive（TAR） model.