基于偏最小二乘回归法的飞机总工时预测模型研究

固体力学与飞行器总体设计

本期目录 | 过刊浏览 | 高级检索

前一篇 | 后一篇

基于偏最小二乘回归法的飞机总工时预测模型研究

王明珠¹, 邓寅东², 常秀娟³

1. 中国航空规划建设发展有限公司工程技术研究院, 北京 100120;
2. 中国航空规划建设发展有限公司发展规划部, 北京 100120;
3. 中国航空规划建设发展有限公司规划咨询研究院, 北京 100120

收稿日期:2011-09-28 修回日期:2011-10-24 出版日期:2012-08-25 发布日期:2012-08-23
通讯作者: 王明珠 E-mail:wang_mingzhu@hotmail.com
基金资助:
航空科学基金(2010ZG17001)

Estimation Model of Plane Manhours in Manufacture Based on Partial Least-squares Regression

WANG Mingzhu¹, DENG Yindong², CHANG Xiujuan³

1. Engineering & Technology Research Institute, China Aviation Planning and Construction Development Co., Ltd., Beijing 100120, China;
2. Division of Strategy Planning, China Aviation Planning and Construction Development Co., Ltd., Beijing 100120, China;
3. Planning and Consultancy Research Institute, China Aviation Planning and Construction Development Co., Ltd., Beijing 100120, China

Received:2011-09-28 Revised:2011-10-24 Online:2012-08-25 Published:2012-08-23
Supported by:
Aeronautical Science Foundation of China (2010ZG17001)

摘要/Abstract

摘要： 从影响军用飞机生产制造工时的众多因素中提取出24个飞机总工时影响因素,采用统计学方法结合理论分析对此24个因素进行科学筛选,筛选出飞机最大起飞重量、最大速度、爬升率、最大过载、钛铝合金比例、复合材料与铝合金比例这6个关键影响因素。考虑偏最小二乘回归(PLS)法在处理小样本多元数据方面的优势,采用PLS法对飞机总工时进行预测,预测结果表明PLS预测模型平均检验误差约为10%。该模型在实际使用过程中,只需获得飞机性能指标和材料构成等少数设计参数即可在飞机产品生产制造前对飞机生产制造总工时进行宏观预测,具有参数少、物理意义明晰、操作简单、便于使用、准确率高等特点,可为缺乏详细设计信息和生产信息的飞机研制早期方案优选、设计优化或对其进行费用分析和成本控制、固定资产投资、安排生产计划等工作提供相对准确的飞机产品工时。

关键词: 飞机总工时, 特征参数, 预测模型, 偏最小二乘回归法, 小样本多元数据

Abstract: Out of a selection of 24 parameters from numerous factors which correlate to plane manhours in manufacture, six key parameters, including maximum takeoff weight, maximum speed, climbing rate, maximum overload, ratio of titanium/aluminum alloy and ratio of composite/aluminum alloy, are chosen via statistical and theoretical analysis based on existing plane samples. In view of the advantages of partial least-squares regression (PLS) method in analyzing multivariate data with small samples, it is utilized to build an estimation model of plane manhours in manufacture. The results show that the average error is about 10%. With this model, very little information, such as performance index, material composition, etc., is needed for the estimation of plane manufacturing manhours before the start of manufacturing activities. The PLS estimation model exhibits many advantages such as less parameters requirement, perspicuous physical meaning, and simple operation. It can be used to predict the manhours for plan optimization, design optimization, cost analysis and control, capital asset investment and production arrangement in the preliminary development stage of a plane with the absence of detailed design and manufacture information.

Key words: plane manhour, characteristic parameter, estimation model, partial least-squares regression method, multivariate data with small samples

中图分类号:

V262
V22

王明珠, 邓寅东, 常秀娟. 基于偏最小二乘回归法的飞机总工时预测模型研究[J]. 航空学报, 2012, 33(8): 1448-1454.

WANG Mingzhu, DENG Yindong, CHANG Xiujuan. Estimation Model of Plane Manhours in Manufacture Based on Partial Least-squares Regression[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2012, 33(8): 1448-1454.

参考文献

[1] Li X D, Zhang H X. Prediction of aircraft fuselage development cost by support vector machines based on rough sets theory. Changsha Aeronautical Vocational and Technical College Journal, 2006, 6(4): 33-36. (in Chinese) 李新东, 张恒喜. 基于粗支持向量机的飞机机体研制费用预测. 长沙航空职业技术学院院报, 2006, 6(4): 33-36.
[2] Zhang H X, Guo J L, Zhu J Y. Multivariate data analysis methods and applications with few observations. Xi’an: Northwestern Polytechnical University Press, 2002. (in Chinese) 张恒喜, 郭基联, 朱家元, 等. 小样本多元数据分析方法及应用. 西安: 西北工业大学出版社, 2002.
[3] Zhang B. The application of gray system theory in estimation of civil aircraft production cost. Journal of Beijing University of Aeronautics and Astronautics, 1993, 19(3):127-132. (in Chinese) 张兵. 灰色系统理论在民用飞机生产成本预测中的应用. 北京航空航天大学学报, 1993, 19(3): 127-132.
[4] Yan Y, Zhang Z M, Tian X T, et al. Exploring aircraft product cost estimation based on activity. Machinery Design & Manufacture, 2008(10): 229-231. (in Chinese) 闫彦, 张振明, 田锡天, 等. 基于作业成本法的飞机产品成本估算研究. 机械设计与制造, 2008(10): 229-231.
[5] Li D K, Zhang H X, Li S A. Development cost estimation of aircraft frame based on BP neural networks. Fire Control and Command Control, 2006, 31(9): 81-83. (in Chinese) 李登科, 张恒喜, 李寿安. BP神经网络的飞机机体研制费用估算. 火力与指挥控制, 2006, 31(9): 81-83.
[6] Li S A, Zhang H X, Tong Z X, et al. Application of partial least-squares regression to the acquisition cost estimating of military aircrafts. Acta Aeronautica et Astronautica Sinica, 2006, 27(3): 96-100. (in Chinese) 李寿安, 张恒喜, 童中翔, 等. 偏最小二乘回归在军用飞机价格预测中的应用. 航空学报, 2006, 27(3): 96-100.
[7] Levenson G S, Barro S M. Cost-estimating relationships for aircraft airframes. Santa Monica: The RAND Corporation. RM-4845-PR, 1966.
[8] Levenson G S, Boren H E, Jr., Tihansky D P, et al. Cost-estimating relationgships for aircraft airframes. Santa Monica: The RAND Corporation. R-761-PR, 1972.
[9] Large J P. Parametric equations for estimating aircraft airframe cost. Santa Monica: The RAND Corporation. R-1693-1-PA&E, 1976.
[10] Hess R W, Romanoff H P. Aircraft airframe cost estimating relationships: study approach and conclusions. Santa Monica: The RAND Corporation. R-3255-AF, 1987.
[11] Resetar S A, Rogers J C, Hess R W. Advanced airframe structural materials: a primer and cost estimating methodology. Santa Monica: The RAND Corporation. R-4016-AF, 1991.
[12] Younossi O, Kennedy M, Graser J C. Military airframe cost: the effects of advanced materials and manufacturing. Santa Monica: The RAND Corporation. MR-1370-AF, 2001.
[13] Chang X J. Introduction to the aircraft airframe cost model of the RAND Corporation. Consultation Research, 2008, 10(4): 1-7. (in Chinese) 常秀娟. 解读兰德公司的飞机机体成本估算模型. 咨询研究, 2008, 10(4): 1-7.
[14] Wang H W. Partial least-squares regression method and applications. Beijing: National Defense Industry Press, 1999. (in Chinese) 王惠文. 偏最小二乘回归方法及其应用. 北京: 国防工业出版社, 1999.
[15] Wang H W, Wu Z B, Meng J. Partial least-squares regression—linear and nonlinear methods. Beijing: National Defense Industry Press, 2006. (in Chinese) 王惠文, 吴载斌, 孟洁. 偏最小二乘回归的线性与非线性方法. 北京: 国防工业出版社, 2006.

E-mail：hkxb@buaa.edu.cn

关于我们

期刊社服务

专业学科

封面文章

友情链接

主管单位：中国科学技术协会主办单位：中国航空学会北京航空航天大学

基于偏最小二乘回归法的飞机总工时预测模型研究

Estimation Model of Plane Manhours in Manufacture Based on Partial Least-squares Regression

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价

[1]	颜黎明, 赵冬冬, 焦宁飞. 基于鲁棒模型的航空交流感应电机预测转矩控制[J]. 航空学报, 2021, 42(9): 324700-324700.
[2]	郑威, 陈怀海. MIMO随机振动试验控制的逆多步预测模型法[J]. 航空学报, 2020, 41(2): 223000-223000.
[3]	苏东林, 郑昊鹏. 一种解决经验模态分解端点效应的边界延拓法[J]. 航空学报, 2016, 37(3): 960-969.
[4]	朱纪洪, 和阳, 黄志毅. 舵机特征模型及其故障检测方法[J]. 航空学报, 2015, 36(2): 640-650.
[5]	丁建立, 周磊. 基于航迹分割的航空器噪声预测模型[J]. 航空学报, 2014, 35(4): 1102-1110.
[6]	张弦, 王宏力. 基于贯序正则极端学习机的时间序列预测及其应用[J]. 航空学报, 2011, 32(7): 1302-1308.
[7]	陈国定;刘曼利;刘亚军;陈晨. 不同流型下轴承腔中油气介质的流动特征参数[J]. 航空学报, 2010, 31(12): 2400-2406.
[8]	王礼沅;郭基联;张恒喜. 递阶偏最小二乘回归在飞机研制费用预测中的应用[J]. 航空学报, 2009, 30(8): 1380-1384.
[9]	郭阳明;姜红梅;翟正军. 基于灰色理论的自适应多参数预测模型[J]. 航空学报, 2009, 30(5): 925-931.
[10]	孙博;康锐;张叔农. 基于特征参数趋势进化的故障诊断和预测方法[J]. 航空学报, 2008, 29(2): 393-398.
[11]	张丹;张卫红;万敏;王继峰;卜昆. 基于位移场仿真与特征参数提取的精铸模具型面逆向设计方法[J]. 航空学报, 2006, 27(3): 509-514.
[12]	孙姝;郭荣伟. 平面埋入式进气道的口面参数选择与试验验证[J]. 航空学报, 2005, 26(3): 268-275.
[13]	王志智;聂学州. 一种变幅载荷下裂纹扩展预测模型[J]. 航空学报, 1987, 8(4): 186-190.