基于改进CBR算法特征权重分配的震后应急物资需求预测方法

打开文本图片集

中图分类号：TP391 文献标识码：A 文章编号：2096-4706（2025）07-0133-06

Abstract：Inorder toimprove theaccuracyofpost-earthquake emergencymaterial demandforecasting，this paper proposes afeatureweightllocationmethodbasedonimprovedCase-BasedReasoning（CBR）algorithm，andconstructsapost-earthquake emergencymaterial demand forecasting modelbasedonsafetystock theory.The model isbasedonseven earthquakedisaster indicatorssuchasagntude，focaldepth，artquakeocrecetime，populationdensityumberofousecollaps，eisic fortificationintensityandseismicintensity.Itcanacuratelyforecastthedemandforvarioustypesofemergencymaterialsafter theearthquake.The experimentalresults show thatthe MeanRelative Errorof the forcast valueobtained bythe forecasting model optimized bygame theory-improved geneticalgorithm（SAGA）and Analytic Hierarchy Process （AHP）algorithmare 89 . 5 7 % and 8 7 . 5 1 % lower than that obtained by GA algorithm optimization and SAGA algorithm optimization，respectively. This showsthat the modelcan providestrong technicalsupport for theeffcientallocationofpost-earthquake emergency materials.

Keywords： post-earthquake emergency material; demand forecasting; game theory; SAGA algorithm; Case-Based Reasoning algorithm

0 引言

中国位于欧亚地震带和环太平洋地震带之间，地震灾害的频繁发生严重威胁着国家的社会建设、经济发展和人民生命安全[。（剩余7281字）