火灾损失预测的改进GM(1,1)模型

An Improved Grey GM(1,1) Model for Prediction of Fire Losses

本文对随机性较强的火灾事故,提出了采用改进GM(1,1)模型来减小预测误差.该模型通过三次改进提高预测精度,首先基于普通GM(1,1)模型,改进模型中初始值提高模型精度;其次基于初值改进后的GM(1,1)模型进行残差修正,再次提高预测准确性;最后对残差修正模型中的初始值进行改进,使最后预测模型更加精确.并且在处理含负值的残差数列时,提出了二次累加的方法进行模型预测.通过普通模型的预测值与改进模型的预测值进行对比,可以发现改进后模型的预测值更加接近实际值.结果表明,三次改进后的GM(1,1)模型精度明显提高,为以后预测研究提供一种理论参考.

An improved GM （ 1, 1 ） model is proposed to reduce the predicting errors of fire accidents with high ran- domicity. The model is made better for three times. Firstly, the improvement of initial condition enhances the accura- cy of the model based on the original GM （ 1,1 ） model ; secondly, we improve the prediction accuracy by the residual modification model based on the improved model of initial condition;at last, the initial condition of the residual modi- fication model is enhanced again so that the final prediction results are more accurate. And in deal with the residual sequence with negative numbers, the secondary accumulation. Compared with the original GM （ 1, 1 ） model, it is found that the prediction results are close to the actual, which indicates that the prediction accuracy is significantly improved.