Latent Structure Modeling and Predictive Quality Control Based on Multi-source Data Streams in the Auto Body Assembly Processes

Abstract

Abstract: This paper present a systematic review for the studies on assembly accuracy insurance. Then, the shortcomings of the concurrent data-driven dimension assembly quality control methods were analyzed, and the latent structure modeling and predictive quality control method was proposed as to the characteristics of the measurement data of the process and product data sets. By extracting the principle components from the data, the partial least squares regression model for assembly deviation propagation were constructed. Furthermore, the assembly quality prediction and control under the conditions of current processes and product inspection strategies might be realized. A side rail assembly case was used to illustrate the proposed procedures. The partial least squares modeling, the quality qualification rate prediction of key features and optimizations of variation sources' variance were used, and the 6?? values of assembly key product features are decreased by about 25%.

Key words: auto body dimension, assembly accuracy, data-driven, quality control, latent structure modeling

摘要： 在对制造过程装配精度监控、诊断等方法进行综述的基础上，分析了现有车身质量检测系统下数据流的特点，总结现有基于数据驱动的装配精度控制方法的问题，提出了基于潜结构建模的车身多工位装配偏差预测控制方法，通过对多元检测数据主向量的提取与偏最小二乘回归模型的构建，实现了现有车身产品检测条件下的装配质量预测与控制。将该方法应用于车身前纵梁装配总成的质量控制案例，通过偏差数据流的偏最小二乘建模，实现总成关键特征的质量合格率预测与零部件质量的优化控制。数值仿真分析结果表明，经工艺优化后，总成测点波动6σ值平均下降了25%左右。

关键词: 车身尺寸, 装配精度, 数据驱动, 质量控制, 潜结构建模

CLC Number:

TH166

LIU Yinhua, SUN Rui, WU Huan. Latent Structure Modeling and Predictive Quality Control Based on Multi-source Data Streams in the Auto Body Assembly Processes[J]. China Mechanical Engineering.

刘银华, 孙芮, 吴欢. [质量优化]基于车身尺寸数据流潜结构建模的装配质量预测控制[J]. 中国机械工程.

References

[1]LEISHMAN R C, CHASE K W. Direct Linearization Method Kinematic Variation Analysis[J]. Journal of Mechanical Design, 2010, 132(7): 071003-1-9.
[2]CHEN Hua, JIN Sun, LI Zhimin, et al. A Solution of Partial Parallel Connections for the Unified Jacobian-Torsor Model[J]. Mechanism & Machine Theory, 2015, 91: 39-49.
[3]LIU S C, HU S J. Variation Simulation for Deformable Sheet Metal Assemblies Using Finite Element Methods[J]. Journal of Manufacturing Science & Engineering, 1997, 119(3): 368-374.
[4]MERKLEY K. Tolerance Analysis of Compliant Assemblies[D]. Provo: Brigham Young University, 1998.
[5]CHOI W, CHUNG H. Variation Simulation of Compliant Metal Plate Assemblies Considering Welding Distortion[J]. Journal of Manufacturing Science & Engineering, 2015, 137(3): 330-351.
[6]UNGEMACH G, MANTWILL F. Efficient Consideration of Contact in Compliant Assembly Variation Analysis[J]. Journal of Manufacturing Science & Engineering, 2009, 131(1): 894-898.
[7]JIN Jionghua, SHI Jianjun. State Space Modeling of Sheet Metal Assembly for Dimensional Control[J]. Journal of Manufacturing Science & Engineering, 1999, 121(4): 756-762.
[8]SHI Jianjun. Stream of Variation Modeling and Analysis for Multistage Manufacturing Processes[J]. Technometrics, 2009(4): 479-480.
[9]刘强, 秦泗钊. 过程工业大数据建模研究展望[J]. 自动化学报, 2016, 42(2): 161-171.
LIU Qiang, QIN Sizhao. Perspectives on Big Data Modeling of Process Industries[J]. Acta Automatica Sinica, 2016, 42(2): 161-171.
[10]KEOGH E, KASETTY S. On the Need for Time Series Data Mining Benchmarks: a Survey and Empirical Demonstration[J].Data Mining & Knowledge Discovery, 2003, 7(4):349-371.
[11]RAKTHANMANON T, CAMPANA B, MUEEN A, et al. Addressing Big Data Time Series: Mining Trillions of Time Series Subsequences under Dynamic Time Warping[J]. ACM Transactions on Knowledge Discovery from Data, 2013, 7(3): 1-31.
[12]周昊飞, 刘玉敏. 基于深度置信网络的大数据制造过程实时智能监控[J]. 中国机械工程, 2018, 29(10): 1201-1207.
ZHOU Haofei, LIU Yunmin. Real-time Intelligent Monitoring for Manufacturing Processes with Big Data Based on Deep Belief Networks[J]. China Mechanical Engineering, 2018, 29(10): 1201-1207.
[13]LIU Y G, HU S J. Assembly Fixture Fault Diagnosis Using Designated Component Analysis[J]. Journal of Manufacturing Science & Engineering, 2005, 127(2): 358-368.
[14]YANG Qingyu, JIN Jionghua. Separation of Individual Operation Signals from Mixed Sensor Measurements[J]. IIE Transactions, 2012, 44(9): 780-792.
[15]SONG K, JANG P Y, CHO H, et al. Partial least Square-based Model Predictive Control for Large-scale Manufacturing Processes[J]. IIE Transactions, 2002, 34(10): 881-890.
[16]JIN Sun, LIU Yinhua, LIN Zhongqin. A Bayesian Network Approach for Fixture Fault Diagnosis in Launch of the Assembly Process[J]. International Journal of Production Research,2012,50(23): 6655-6666.
[17]LIU Jian, SHI Jianjun, HU S J. Engineering-driven Factor Analysis for Variation Source Identification in Multistage Manufacturing Processes[J].Journal of Manufacturing Science & Engineering, 2015, 130(4): 1-31.
[18]王惠文. 偏最小二乘回归方法及其应用[M]. 北京：国防工业出版社, 1999: 91-177.
WANG Huiwen.Partial Least-squares Regression Method and Applications[M].Beijing:National Defense Industry Press, 1999: 91-177.