基于XGBoost的车身尺寸装配质量智能预测模型

doi:10.3969/j.issn.1007-7375.2021.03.010

工业工程 ›› 2021, Vol. 24 ›› Issue (3): 77-82.doi: 10.3969/j.issn.1007-7375.2021.03.010

基于XGBoost的车身尺寸装配质量智能预测模型

董海¹, 冯晔²

1. 沈阳大学应用技术学院;
2. 机械工程学院，辽宁沈阳 110044

收稿日期:2020-03-04 发布日期:2021-06-26
作者简介:董海(1971-)，男，山东省人，教授，博士，主要研究方向为生产计划与调度、供应链管理和质量管理等
基金资助:
国家自然科学基金资助项目（71672117）；辽宁省重点研发计划资助（2019JHB/1020024）

An Intelligent Prediction Model of Body Size Assembly Quality Based on XGBoost Algorithm

DONG Hai¹, FENG Ye²

1. School of Applied Technology;
2. School of Mechanical Engineering, Shenyang University, Shenyang 110044, China

Received:2020-03-04 Published:2021-06-26

摘要/Abstract

摘要： 针对汽车多级制造系统中传统机器学习方法处理多元数据样本时间久、精度低等问题，提出一种基于XGboost的车身尺寸装配质量智能预测模型，解决多级制造系统的车身装配精准预测控制问题。首先，通过对车身多级装配过程的分析，对数据样本进行预处理，建立基于Spearman系数的不同特征要素的绝对相关性矩阵；其次，对生产流程的相关数据实时采集、清洗及挖掘分析，提出数据分析流程与数据处理框架，建立基于XGBoost的车身尺寸装配质量智能预测模型，并通过对模型性能的有效评估实现对车身尺寸装配的精准控制；最后，仿真实例对比分析表明，基于XGboost的质量智能预测模型能精准地解决多级制造系统中的车身装配质量控制问题。

关键词: 多级制造系统, 车身尺寸, 质量预测, XGBoost算法

Abstract: Aiming at the problems of long processing time and low accuracy of the traditional machine learning method in the multi-level manufacturing system of the automobile, an intelligent prediction model of body size and assembly quality based on XGBoost is proposed to solve the problem of accurate predictive control of the multi-level manufacturing system body assembly. Firstly, the multi-level assembly process of the car body is analyzed, the data samples processed, and the absolute correlation matrix of different feature elements established based on Spearman coefficients. Secondly, through a real-time collection, cleaning and mining analysis of relevant data in the production process, the data analysis process and data processing framework are proposed, an intelligent prediction model of body size and assembly quality based on XGBoost established, and the effective evaluation of model performance conducted to ensure accurate control of body size assembly. Finally, an example shows that the XGBoost quality intelligent prediction model can solve the problem of car body assembly quality control in multi-level manufacturing systems.

Key words: multistage manufacturing system, auto body dimension, quality prediction, XGBoost

中图分类号:

TP395

董海, 冯晔. 基于XGBoost的车身尺寸装配质量智能预测模型[J]. 工业工程, 2021, 24(3): 77-82.

DONG Hai, FENG Ye. An Intelligent Prediction Model of Body Size Assembly Quality Based on XGBoost Algorithm[J]. Industrial Engineering Journal, 2021, 24(3): 77-82.

参考文献

[1] 刘银华, 孙芮, 吴欢. 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, 2019, 30(2): 237-243
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, 2019, 30(2): 237-243
[2] YANG K. Improving automotive dimensional quality by using principal component analysis[J]. Quality and Reliability Engineering International, 1996, 12(6): 401-409
[3] HU S J, KOREN Y. Stream-of-variation theory for automotive body assembly[J]. CIRP Annals, 1997, 46(1): 1-6
[4] SONG K, YOLJANG P, CHO H, et al. Partial least square-based model predictive control for large-scale manufacturing processes[J]. IIE Transactions, 2002, 34(10): 881-890
[5] 赫立远. 基于统计过程分析的华晨某款白车身制造尺寸质量改进[D]. 长春: 吉林大学, 2017.
HE Liyuan. A brilliance-auto BIW manufacturing dimension quality improvement based on statistical process analysis[D]. Changchun: Jilin University, 2017.
[6] KWAK D S, KIM K J. A data mining approach considering missing values for the optimization of semiconductor manufacturing processes[J]. Expert Systems with Applications, 2012, 39(3): 2590-2596
[7] KIM D, KANG P, CHO S, et al. Machine learning based novelty detection for faulty wafer detection in semiconductor manufacturing[J]. Expert Systems with Applications, 2012, 39(4): 4075-4083
[8] RAHMAN A, SMITH D V, TIMMS G. A novel machine learning approach toward quality assessment of sensor data[J]. IEEE Sensors Journal, 2014, 14(4): 1035-1047
[9] MARTIN Ó, PEREDA M, SANTOS J I, et al. Assessment of resistance spot welding quality based on ultrasonic testing and tree-based techniques[J]. Journal of Material Processing Technology, 2014, 214(11): 2478-2487
[10] HEBERT J. Predicting rare failure events using classification trees on large scale manufacturing datawith complex interactions[C]. 2016 IEEE International Conference on Big Data (Big Data), Washington DC: IEEE, 2016.
[11] ZHANG D, QIAN L, MAO B, et al. A data-driven design for fault detection of wind turbines using random forests and XGboost[J]. IEEE Access, 2018, 6: 21020-21031
[12] BAHAGHIGHAT M, AKBARI L, XIN Q. A Machine learning-based approach for counting bister cards within drug packages[J]. IEEE Access, 2019, 7: 83785-83796
[13] 刘建文. 基于零件特征及柔性夹具优化的装配偏差分析[D]. 长沙: 湖南大学, 2017.
LIU Jianwen. Assembly deviation analysis based on part feature and flexible fixture optimization[D]. Changsha: Hunan University, 2017.

基于XGBoost的车身尺寸装配质量智能预测模型

An Intelligent Prediction Model of Body Size Assembly Quality Based on XGBoost Algorithm

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价