多源信息分级优化备件需求预测模型  

Multi-source information classification optimization based spare parts demand prediction model

作　　者：索海龙[1] 高建民[1] 高智勇[1] 刘元浩 

机构地区：[1]机械制造系统工程国家重点实验室(西安交通大学),西安710049 [2]西安陕鼓动力股份有限公司,西安710611

出　　处：《中国科技论文》2015年第22期2601-2606,共6页China Sciencepaper

基　　金：国家科技支撑计划资助项目(2012BAF12B04)

摘　　要：为了解决大型动力装备制造供应企业主关键备件需求预测难的问题,采用来自企业多部门的多源异构信息,对其进行整理、归类和分析,建立了一种基于多源信息分级优化备件需求预测模型。该模型主要包括备件基本库的建立、基于客户满足率的模型优化、基于备件储备策略的模型优化和基于产品服役状态的模型优化。分级优化备件需求预测方法分别与时序预测方法、企业实际预测方法得到的备件数量通过实例进行对比验证分析,该模型实际满足率分别由90.32%和98.81%提高到98.87%,对大型装备主关键备件的需求预测具有实际可行性和良好经济性。In order to solve the difficult demand prediction problem of main key spare parts in large power equipment manufacturing supply enterprises,the multi-source heterogeneous information from multisectoral departments was trimmed,classified and analyzed,and a spare parts demand prediction model based on multi-source information classification optimization was proposed.This model mainly included the establishment of the basic spare parts inventory,the model optimization of customer satisfaction rate,spare parts reserve strategy and the product service status.The spare parts results from hierarchical optimization prediction model,combined with time series forecasting method and enterprise actual forecasting methods respectively were analyzed by an actural example.Model actual satisfied rate is improved from 90.32% and 98.81% respectively to 98.87%.Meanwhile,practical feasibility and economical efficiency were verified for large equipment main key spare parts demand prediction.

关 键 词：大型动力装备 多源信息 备件 分级优化预测 

分 类 号：F426.4[经济管理—产业经济] TB114.3[理学—概率论与数理统计]