摘要
针对横截面数据的复杂装备费用预测问题,由于主要参数比较相似的装备系统其研制费用往往趋同,提出了横截面数据的"相似信息优先原理"。分析新研装备与以往装备的相似度,按照指标信息的相似度区分横截面信息的优先次序。用归一化的相似度作为加权最小二乘法的权重,通过实例建立相似信息优先的回归模型,并与其他方法的结果对比,结果表明本文的方法具有更高的预测精度,相似信息优先的多元回归模型充分反映了相似信息的规律。
The similar information priority principle is put forward in order to predict the complicated equip ment costs from the data of the cross section, because the similar main parameters of complicated equipment systems often lead to the similar cost. The similarity between new researched equipment and past equipment is analyzed, and the information priorities are distinguished according to the similarity of index cross section information. The normalized similarity is regarded as the weight of the weighted least squares, the regression model with similar information priority is set up, and the results are compared with other methods. The results of three examples show that the proposed method has higher prediction precision, and the multiple regression mo- del with similar information priority reflects the similar information law.
出处
《系统工程与电子技术》
EI
CSCD
北大核心
2014年第10期2024-2028,共5页
Systems Engineering and Electronics
基金
欧盟第7研究框架玛丽.居里国际人才引进计划Fellow项目(FP7-PIIF-GA-2013-629051)
国家自然科学基金(71171113
71173106)
国家社科基金重点项目(12AZD102)
国家科技重大专项(2009ZX11002)
中央高校基本科研业务费专项基金(NP2014105)
国家级教学团队基金(10td128)
南京航空航天大学引进人才基金(1009-YAH14003)资助课题
关键词
复杂装备费用
灰色系统理论
多元回归
相似信息优先原理
complicated equipment cost
grey system theory
multiple regression model
similar informa- tion priority principle