系统工程与电子技术 ›› 2024, Vol. 46 ›› Issue (4): 1309-1319.doi: 10.12305/j.issn.1001-506X.2024.04.19

• 系统工程 • 上一篇    下一篇

基于灰色关联协同效应权重配置的费用预测模型

赵潞1,*, 方志耕1, 于亮2, 张亚东1, 邱玺睿1, 华晨晨1   

  1. 1. 南京航空航天大学经济与管理学院, 江苏 南京 211106
    2. 中国航天科技集团有限公司, 北京 100048
  • 收稿日期:2022-10-26 出版日期:2024-03-25 发布日期:2024-03-25
  • 通讯作者: 赵潞
  • 作者简介:赵潞 (1999—), 男, 硕士研究生, 主要研究方向为复杂装备成本管理与控制
    方志耕 (1962—), 男, 教授, 博士研究生导师, 博士, 主要研究方向为可靠性工程、复杂装备研制管理
    于亮 (1987—), 男, 研究员, 硕士, 主要研究方向为复杂装备研制过程管理、工业经济、企业经济
    张亚东 (1996—), 男, 硕士研究生, 主要研究方向为可靠性增长
    邱玺睿 (1999—), 男, 硕士研究生, 主要研究方向为卫星效能评估
    华晨晨 (1999—), 女, 硕士研究生, 主要研究方向为效能优化

Cost prediction model based on grey relational synergistic effect weight allocation

Lu ZHAO1,*, Zhigeng FANG1, Liang YU2, Yadong ZHANG1, Xirui QIU1, Chenchen HUA1   

  1. 1. College of Economics and Management, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
    2. China Aerospace Science and Technology Corporation, Beijing 100048, China
  • Received:2022-10-26 Online:2024-03-25 Published:2024-03-25
  • Contact: Lu ZHAO

摘要:

费用预测是复杂装备成本管理的核心内容。在同类型复杂装备仅有少量样本信息的情况下, 为提高估算预测精度, 解决贫信息下费用影响要素筛选困难、要素间由于协同效应导致的权重分配不合理、费用预测误差较大等问题, 提出了一种基于灰色关联协同效应贡献度分配的要素权重配置方法。首先通过灰色关联度分析筛选相似样本及费用关键影响要素; 然后, 依据各要素在协同效应下对灰色关联度提高的贡献程度大小, 参考Shapley值思想计算各要素的灰色比较关联重要性, 以此确定权重; 最后, 构建相应的异阶参数灰色分数阶预测模型, 对目标装备进行费用预测。通过与已有文献中的方法进行对比, 结果表明所提方法有较高的预测精度且具有一定的适用性, 能够挖掘小样本下费用影响要素间的潜在信息, 更可以合理地分配要素权重, 提高费用预测精度。

关键词: 复杂装备费用, 协同效应, Shapley值, 灰色关联分析, 灰色分数阶GM(0, N)模型

Abstract:

Cost estimation is the core content of complex equipment cost management. In the case that only a small amount of sample information is available for the same type of complex equipment, in order to improve the estimation and prediction accuracy, and to solve the problems of difficult screening of cost-influencing elements under poor information, unreasonable weight distribution among elements due to synergistic effects, and large cost prediction errors, a method for allocating element weights based on the contribution of grey relational synergistic effects is proposed. Firstly, similar samples and key cost influencing elements are screened by grey relational analysis. Secondly, based on the contribution of each element to the improvement of grey relational grade under the synergistic effect, the grey comparative relational importance of each element with reference to the idea of Shapley value is calculated, and thus the weights are determined. Finally, the corresponding heterogeneous order parameter grey fractional order prediction model is constructed for cost prediction of target equipment. By comparing with the existing methods in the literatures, the comparison results show that the proposed method has a high prediction accuracy and certain applicability, indicating that the proposed method can explore the potential information among the cost-influencing elements in a small amount of sample, assign the element weights more reasonably and improve the accuracy of cost prediction.

Key words: complex equipment costs, synergistic effect, Shapley value, grey relational analysis, grey fractional order GM (0, N) model

中图分类号: