稳健GIM(1)预测模型及其应用

A Robust GIM(l) Forecasting Model and Its Application

结合某水域地面水BOD_5的预测实践,研究提出了稳健GIM（1）预测模型。该模型的参数估计运用最小残差绝对和算法,并探讨了其较常规最小二乘法在处理含异常值的系统的优点。实例表明,稳健GIM（1）模型比常规GIM（1）模型的预测更可行。

Combining the forecasting practice in BOD5 of some surface water, a robust GIM (1) is set up and studied. Parameters estimation of the new model based on least absolute sum of residues (LA) is introduced. The advantage of LA algorithm over the least square(LS) method has been verified by using the treatment of system with individual abnormal value. A practical example shows that the forecasting feasibility of the robust GIM(l) model is better than the corresponding traditional model.