摘要
应用灰色预测理论对我国火灾事故四项指标进行预测研究。以2001-2008年的火灾统计数据为原始数据序列,分别建立GM(1,1)预测模型和中心逼近式GM(1,1)预测模型,并对原始数据进行拟合分析以评估模型精度;利用这两个预测模型对2009、2010年的火灾事故数据进行预测,并与实际值比较分析。结果表明,中心逼近式GM(1,1)模型的拟合精度及预测精度均高于传统GM(1,1)模型,但这两个模型不适用于火灾事故直接经济损失的预测,其余三项指标的中心逼近式GM(1,1)模型的预测精度能够达到一级。
The prediction of four indicators of fire accident in China is studied with grey prediction theory.Taking the fire annual statistics data of 2001-2008 as the original data series,the GM（1,1） model and the center approach GM（1,1） model were established respectively,and the accuracy of these two models was evaluated by fitting to the original data.Then,the fire accident data of 2009 and 2010 is predicted by using these two models,and the results are compared with the actual value.The result indicates that,the fitting accuracy and prediction accuracy of the center approach GM（1,1） model are both higher than that of traditional GM（1,1） model.These two models are neither suitable in prediction of the directly economic loss of fire accident,the accuracy of the center approach GM（1,1） models of other three indicators can achieve the first level.
出处
《消防科学与技术》
CAS
北大核心
2014年第2期213-216,共4页
Fire Science and Technology
关键词
火灾事故
灰色预测
中心逼近
背景值
拟合
后验差检验
fire accident
grey prediction
center approach
background value
fitting
latter error checking
