计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (11A): 240300123-8.doi: 10.11896/jsjkx.240300123

• 交叉&应用 • 上一篇    下一篇

小样本飞机生产质量偏差数据分析与预测方法研究

王陆航1, 张冬冬2, 卢鹄3, 李汝鹏3, 葛小丽3   

  1. 1 同济大学数学科学学院 上海 200092
    2 同济大学电子与信息工程学院 上海 201804
    3 上海飞机制造有限公司航空制造技术研究所 上海 201324
  • 出版日期:2024-11-16 发布日期:2024-11-13
  • 通讯作者: 张冬冬(ddzhang@tongji.edu.cn)
  • 作者简介:(2050032@tongji.edu.cn)
  • 基金资助:
    国家重点研发计划(2021YFB3301901)

Study on Analysis and Prediction Method of Small Sample Aircraft Production QualityDeviation Data

WANG Luhang1, ZHANG Dongdong2, LU Hu3, LI Rupeng3, GE Xiaoli3   

  1. 1 School of Mathematical Sciences,Tongji University,Shanghai 200092,China
    2 College of Electronic and Information Engineering,Tongji University,Shanghai 201804,China
    3 Aviation Manufacturing Technology Research Institute,Shanghai Aircraft Manufacturing Co.,Ltd.,Shanghai 201324,China
  • Online:2024-11-16 Published:2024-11-13
  • About author:WANG Luhang,born in 2002,undergraduate.His main research interest is aircraft production quality control.
    ZHANG Dongdong,born in 1977,Ph.D,professor,Ph.D supervisor.Her main research interests include image processing and deep learning.
  • Supported by:
    National Key R&D Program of China(2021YFB3301901).

PDF (PC)

164

摘要： 随着现代工业水平和对飞机精度要求的不断提升,对飞机生产质量的分析和管控方法越来越受到各大航空企业的重视。当前阶段,针对飞机装配偏差存在可参考样本数据少、不确定性大、非线性、多层级装配等固有特征,传统的分析方法难以准确地构建飞机生产偏差分析模型。因此,以飞机生产过程的偏差为研究目标,对飞机生产质量偏差数据分析与预测方法展开系统研究。首先分析各个零件之间的偏差关系,基于主成分分析法识别对总偏差影响最大的关键零件,找到重点预测的目标;接着从实际生产的类正态数据出发,重点关注关键零件,实现了基于正态云模型的偏差数据预测、生成与验证,得到更多样本的飞机生产质量偏差数据及其隶属度,一定程度上缓解了“小样本”的问题,并基于k-折交叉验证对预测模型进行了评估;最后构建了基于改进的灰色预测模型的多源数据融合的装配偏差波动区间协同预测模型,“小样本”问题的缓解使得区间预测更加精细、科学,在公差数据的参考下,预测飞机生产质量偏差所在的区间范围,为实际生产和制定公差修正机制提供指导。

关键词: 小样本数据, 飞机生产质量管控, 数学建模, 主成分分析法, 正态云模型, k-折交叉验证, 灰色预测模型

Abstract: With the development of modern industrial capabilities and the demand for increased precision in aircraft,the analysis and control of aircraft production quality have become a focal point for major aerospace enterprises.At the current stage,traditional analytical methods face challenges in accurately constructing deviation analysis models for aircraft production due to inhe-rent features such as limited reference sample data,significant uncertainties,non-linearity,and multi-level assembly deviations.Therefore,this paper focuses on the deviations in the aircraft production process and systematically explores methods for analyzing and predicting aircraft production quality discrepancies.Firstly,this paper analyzes the deviation relationships among various components,identifying the key component with the greatest impact on total deviation based on principal component analysis,which pinpoints the focus for predictive targeting.Subsequently,starting from actual production data resembling a normal distribution,this paper pays special attention to key components,enabling the prediction,generation,and validation of deviation data based on the normal cloud model,which yields aircraft production quality deviation data and their memberships for a greater varietyof samples,alleviating the issue of “small sample” and evaluating the predictive model through k-fold cross-validation.Finally,a cooperative predictive model for assembly deviation fluctuation intervals based on the improved grey forecasting model and multi-source data fusion is established.The alleviation of the “small sample” issue enhances the precision and scientific nature of interval prediction.With reference to tolerance data,predict the interval range where aircraft production quality deviations are located,providing guidance for actual production and the formulation of tolerance correction mechanisms.

Key words: Small sample data, Aircraft production quality control, Mathematical modeling, Principal component analysis, Normal cloud model, K-fold cross validation, Grey forecasting model

中图分类号: 

  • TP399
[1]YU H D,LAI X M,LIN Z Q.Prediction and Control Method of Dimensional Accuracy in Assembly Manufacturing of Large Thin-walled Structures in Aerospace[J].Shanghai Aerospace,2020,37(3):1-10.
[2]SU C,WANG Z,XU H.Analysis of Assembly Deviation ofFlexible Parts Based on Finite Element Method[J].Machinery Manufacturing & Automation,2019(4):79-83.
[3]ZHU P,YU J,ZHENG X,et al.Modeling of Deviation Transmission Network and Error Tracing in Mechanical Assembly Process[J].Journal of Zhejiang University:Engineering Science Edition,2019,53(8):12.
[4]CHENG L.Research on Modeling and Key Technologies of Di-gital Assembly Deviation for Large Aircraft Based on Key Cha-racteristics[D].Hangzhou:Zhejiang University,2014.
[5]SUN H.Analysis and Prediction of Assembly Deviation for Aircraft Panel-like Flexible Components[D].Nanjing:Nanjing University of Aeronautics and Astronautics,2015.
[6]ZHAO D P,TIAN X Y,GENG J H.Prediction of Motion Assembly Accuracy Based on Clearance Connectors and Multi-dimensional Vector Rings[C]//The third National Modern Manufacturing Integration Technology Academic Conference.2014:1-12.
[7]YANG Z J.Research on Predictive Control Theory of Nonlinear Systems in Aircraft[D].Wuhan:Wuhan University of Techno-logy,2006.
[8]HUGUES E,CCR E,CHARPENTIER E,et al.Application of Markov processes to predict aircraft operational reliability[J/OL].2002.https://www.semanticscholar.org/paper/Application-of-Markov-processes-to-predict-aircraft-Hugues-Ccr/bd5be5dea7b4f4beca1206ab9042eb250d5e3118.
[9]WANG B.Study on the Fault Trend of General Aircraft Structure under the Condition of Small Sample Data[D].Deyang:Ci-vil Aviation Flight University of China,2013.
[10]ZHOU F W.Small Sample Analysis of Skin Damage Around B737NG Cargo Door of [J].Aviation Maintenance & Engineering,2021(1):57-59.
[11]LI S A,SONG B F,ZHANG H X.Method for MultivariateAnalysis with Small Sample in Aircraft Cost Estimation[J].Journal of Aircraft,2007,44(3):1042-1045.
[12]DENG B.Prediction and Control of Assembly Deviation Transmission for Aircraft Structural Components Driven by Small Sample Data[D].Nanchang:Nanchang Hangkong University,2021.
[13]CHU G,ZHANG S,JIN S.Research on Deviation Control of Car Body Doors in Sedans[J].Machinery Design & Manufacture,2003(5):3.
[14]HU M,LAI X,LIN Z.Application Research of Principal Com-ponent Analysis Method in Dimensional Deviation of Car Assembly[J].China Mechanical Engineering,2002,13(6):3.
[15]LI F Q,GAO W S.Probability Theory and Mathematical Statistics[M].Jilin:Jilin University Press,2004.
[16]LI C Y,GAO Y G,CUI X M.Research on Prediction of Surface Dynamic Settlement Based on Normal Distribution Time Function[J].Rock and Soil Mechanics,2016(S1):9.
[17]WANG Z N,XIAO M Q,LI Y,et al.Prediction Algorithm of Cloud Model for Log-normal Distribution Data[J].Computer Applications and Software,2009,26(9):3.
[18]LI D Y,MENG H J,SHI X M.Membership Cloud and Its Ge-nerator[J].Journal of Computer Research and Development,1995,32(6):6.
[19]GUO S Z,LIAO X F,XIAN K Y.Logistic Regression Click Prediction Algorithm Based on Composite Structure[J].Computer Science,2024,51(2):73-78.
[20]CAO L,SHANG W,XIE S Y,et al.Research on Price IndexPrediction Based on AGNN Public Opinion Index Network[J].Chinese Journal of Management,2023,20(3):411.
[21]LIU Y H,ZHANG S M,CHU G P.Combination modeling of auto body assembly dimension propagation considering multi-source information for variation reduction[J].Assembly Automation,2019,39(4):514-522.
[22]XUE Z H,ZHANG K.Analysis of Duration Deviation PredictionBased on Grey System Theory[J].Shanxi Architecture,2009,35(8):215-216.
[23]HAN L,LIU X,WANG Z,et al.Integrated Control of Cigarette Rolling Quality Combining Deviation Prediction with Parameter Optimization[J].Packaging Engineering,2023,44(15):217-222.
[24]CHEN P.Research on Principal Component Analysis Methodand Its Application in Feature Extraction[D].Xi'an:Shaanxi Normal University,2014.
[25]ZENG L.Improved Grey Multivariate GM(1,N) Model and Its Application[J].Journal of Southwest University:Natural Science Edition,2019,41(9):9.
[26]ZHOU W,FANG Z G.Research on Nonlinear Optimization GM(1,N) Model and Its Application.Systems Engineering and Electronics,2010(2):5.
[27]FU Z W,YANG Y K,WANG T Y.Prediction of Urban Domestic Water Demand in Haiyan County Based on Improved Nonli-near Optimization GM(1,N) Model[J].Water Resources and Power,2019,37(10):4.
[28]THORDARSON F O,MADSEN H,NIELSEN H A,et al.Conditional weighted combination of wind power forecasts[J].Wind Energy,2010,13(8):751-763.
[29]XU Y Q.Precision Control in Shipbuilding:Mathematical Me-thods of Tolerance Theory[J].Journal of Zhenjiang Shipbuil-ding Institute,1988(Z1):49-58.
[30]MCCULLOCH W S,PITTSW.A Logical Calculus of the Ideas Immanent in Nervous Activity[J].Journal of Symbolic Logic,1943,9(2):49-50.
[31]WACHSMUTH A,WILKINSON L,DALLAL G E.Galton'sBend:An Undiscovered Nonlinearity in Galton's Family Stature Regression Data and a Likely Explanation Based on Pearson and Lee's Stature Data[J/OL].2003.https://www.semanticscholar.org/paper/Galton%27s-Bend%3A-An-Undiscovered-Nonlinearity-in-Data-Wachsmuth-Wilkinson/f1bdfd6b19c6cac497147274cef8a14d448d23b4?p2df.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发