面向多品种小批量制造过程的NAD-EWMA控制图多目标优化设计方法

doi:10.3901/JME.2023.03.232

摘要/Abstract

摘要： 针对面向多品种小批量制造过程设计质量控制图面临的样本数量少、分布不确定问题,提出一种基于非参数、自适应、动态EWMA控制图的多目标优化设计方法。基于非参数统计理论与自适应控制的思想,构建与样本数据分布无关的控制图统计量,并设计一种基于聚类距离的动态抽样方法实现样本抽样;在此基础上,考虑统计性、经济性建立控制图多目标优化设计模型,基于改进人工鱼群算法与云清晰综合评价方法实现对模型求解,进而构建面向多品种小批量制的非参数自适应动态EWMA控制图。最后,以航天复杂构件制造过程为例,对制造过程进行动态监控。结果表明,所提方法能够快速监控到质量异常,监控性能高,验证了该方法的有效性和可行性,为多品种小批量制造过程实际的质量监控提供一种有效的途径。

关键词: 多品种小批量, 质量控制, 非参数统计, EWMA控制图, 人工鱼群算法

Abstract: In view of the problems of small sample size and uncertain distribution in designing quality control charts for multi-variety and small-batch manufacturing processes, a multi-objective optimization design method based on non-parametric, adaptive and dynamic EWMA control charts is proposed. According to the theory of nonparametric statistics and the idea of adaptive control, control chart statistics independent of sample data distribution are constructed, and a dynamic sampling method based on clustering distance is designed to realize sample sampling; On this basis, multi-objective optimization design of the control chart is carried out considering the statistical and economic characteristics. Based on the improved artificial fish swarm algorithm and cloud clear comprehensive evaluation method, the model is solved, and the non parametric adaptive dynamic EWMA control chart for multi variety and small batch system is constructed. Finally, taking the manufacturing process of aerospace complex components as an example, the dynamic monitoring of the manufacturing process is carried out. The results show that the proposed method can quickly monitor the abnormal quality and has high monitoring performance, which proves the effectiveness and feasibility of the method, and provides an effective way for the actual quality monitoring of multi variety and small batch manufacturing process.

Key words: multi-variety and small-batch, quality control, non-parametric statistics, EWMA control chart, AFSA

中图分类号:

TB114

陈克强, 姜兴宇, 刘伟军, 田志强, 徐效文, 李世磊, 索英祁. 面向多品种小批量制造过程的NAD-EWMA控制图多目标优化设计方法[J]. 机械工程学报, 2023, 59(3): 232-248.

CHEN Keqiang, JIANG Xingyu, LIU Weijun, TIAN Zhiqiang, XU Xiaowen, LI Shilei, SUO Yingqi. Quality Control Method of Key Processes in Multi Variety and Small Batch Manufacturing Process Based on NAD-EWMA Control Chart[J]. Journal of Mechanical Engineering, 2023, 59(3): 232-248.

参考文献

[1] ABBASI A,ASLAM M,SAGHIR A. A mixed nonparametric control chart for efficient process monitoring[J]. The International Journal of Advanced Manufacturing Technology,2018,99(9):2549-2561
[2] RIAZ M,ABID M,NAZIR H Z,et al. A non-parametric double homogeneously weighted moving average control chart under sign statistic[J]. Quality and Reliability Engineering,2021,37(4):1544-1560.
[3] LI Zhonghua,XIE Mei,ZHOU Maoyuan. Rank-based EWMA procedure for sequentially detecting changes of process location and variability[J]. Quality Technology & Quantitative Management,2018,15(3):354-373.
[4] ZHOU M Y,ZHOU Q,GENG W. A new nonparametric control chart for monitoring variability[J]. Quality and Reliability Engineering International,2016,32(7):2471-2479.
[5] 赵宇,李艳婷. 面向小样本高维数据的秩检验非参控制图[J]. 中国机械工程,2022,33(9):1104-1114.
ZHAO Yu,LI Yanting. Nonparametric control chart of rank test for small samples of high-dimensional data[J]. China Mechanical Engineering,2022,33(9):1104-1114.
[6] 宋贽,周茂袁,张阚,等. 联合监测过程位置参数和尺度参数的非参数Shewhart控制图[J]. 数理统计与管理,2022,41(1):94-107.
SONG Zhi,ZHOU Maoyuan,ZHANG Kan,et al. A distribution-free Shewhart control chart for joint monitoring of location and scale parameters[J]. Journal of Applied Statistics and Management,2022,41(1):94-107.
[7] 刘浏,邓泽培,张健,等. 一类基于次序秩的带可变抽样区间的非参数动态控制图[J]. 系统科学与数学,2016,36(10):1804-1814.
LIU Liu,DENG Zepei,ZHANG Jian,et al. Dynamic nonparametric control charts with variable sampling interval based on sequential ranks[J]. Journal of Systems Science and Mathematical Sciences,2016,36(10):1804-1814.
[8] 刘浏,张健. 基于次序秩的非参数EWMA联合控制图[J]. 数理统计与管理,2013,32(6):1049-1059.
LIU Liu,ZHANG Jian. A sequential rank-based combined nonparametric EWMA control chart[J]. Journal of Applied Statistics and Management,2013,32(6):1049-1059.
[9] MUKHERJEE A,MAROZZI M. Distribution-free lepage type circular-grid charts for joint monitoring of location and scale parameters of a process[J]. Quality & Reliability Engineering International,2016,33(2):241-274.
[10] Chong Zhilin,MUKHERJEE A,KHOO M B C. Some distribution-free lepage-type schemes for simultaneous monitoring of one-sided shifts in location and scale[J]. Computers & Industrial Engineering,2018,115:653-669.
[11] MUKHERJEE A,SEN R. Optimal design of Shewhart-lepage type schemes and its application in monitoring service quality[J]. European Journal of Operational Research,2018,266(1):147-167.
[12] TANG Anan,SUN Jinsheng,HU Xuelong,et al. A new nonparametric adaptive EWMA control chart with exact run length properties[J]. Computers & Industrial Engineering,2019,(130):404-419.
[13] HAQ A,GUULZAR R,KHOO M B C,et al. An efficient adaptive EWMA control chart for monitoring the process mean[J]. Quality and Reliability Engineering International,2018,34(4):563-571.
[14] 平安,孙金生,胡雪龙,等. 自适应指数加权移动平均指数控制图设计[J]. 统计与决策,2021,37(22):27-31.
PING An,SUN Jinsheng,HU Xuelong,et al. Design of an adaptive exponential weighted moving average exponential control chart[J]. Statistics & Decision 2021,37(22):27-31.
[15] 敖银辉,吴先沛. 带参数估计的加权自适应多元累计和控制图及其应用[J]. 统计与决策,2020,36(10):28-32.
AO Yinhui,WU Xianpei. Weighted adaptive MCUSUM control charts with parameter estimation and its application[J]. Statistics & Decision,2020,36(10):28-32.
[16] ZHAO M J,DRISCOLL A R. The c-chart with bootstrap adjusted control limits to improve conditional performance[J]. Quality and Reliability Engineering International,2016,32(8):2871-2881.
[17] 王海宇. 基于未知分布的小批量Bootstrap控制图[J]. 统计与决策,2014(4):83-85.
WANG Haiyu. Small batch bootstrap control chart based on unknown distribution[J]. Statistics & Decision,2014(4):83-85.
[18] STEINER S H,LEE G P,WESOLOWSKY G O. Shewhart control charts to detect mean and standard deviation shifts based on grouped data[J]. Quality & Reliability Engineering,2015,12(5):345-353.
[19] WIEDERHOLD M,GREIPEL J,OTTONE R,et al.Clustering of similar processes for the application of statistical process control in small batch and job production[J]. International Journal of Metrology and Quality Engineering,2016,7(4):404-412.
[20] 周康渠,游思琦,杨坤. 基于相似性分析的工序质量控制研究及应用[J]. 重庆理工大学学报,2019,33(3):119 -125.
ZHOU Kangqu,YOU Siqu,YANG Kun. Research and application of process quality control based on similarity analysis[J]. Journal of Chongqing University of Technology,2019,33(3):119-125.
[21] 张根保,李立章,冉琰,等. 多品种小批量生产模式下基于相似元的工序能力分析[J]. 工程设计学报,2018,25(1):18-26+34.
ZHANG Genbao,LI Lizhang,RAN Yan,et al. Process capability analysis based on similarity cell under the multiple-variety and small-batch production mode[J]. Chinese Journal of Engineering Design,2018,25(1),18-26.
[22] HU Xuelong,CASTAGLIOLA P. Guaranteed conditional design of the median chart with estimated parameters[J]. John Wiley & Sons,Ltd,2017,33(8):1873-1884.
[23] HU Xuelong,CASTAGLIOLA P,ZHOU X J,et al. Conditional design of the EWMA median chart with estimated parameters[J]. Communications in Statistics-Theory and Methods,2019,48(8):1871-1889.
[24] QUININO R C,HO L L,CRUZ F R B & BESSEGATO L F. A control chart to monitor the process mean based on inspecting attributes using control limits of the traditional X-bar chart[J]. Journal of Statistical Computation and Simulation,2020,90(11):1-22.
[25] TAHIR N,MUHAMMAD A R,HAN D. Generalized multiple dependent state optimal control charts under ranked set sampling for monitoring process mean[J]. Quality and Reliability Engineering International,2020,36(5):1494-1512.
[26] 张驰.基于马尔可夫链模型的MEWMA控制图性能分析与优化[J]. 西安电子科技大学学报,2013,23(3):37-40.
ZHANG Chi. Performance analysis and optimization of MEWMA control chart based on markov chain model[J]. Journal of Xidian University,2013,23(3):37-40.
[27] 胡雪龙,周晓剑,黄卫东,等. 变采样间隔中位数控制图设计[J]. 工业工程与管理,2017,22(4):62-67.
HU Xuelong,ZHOU Xiaojian,HUANG Weidong,et al. Design of variable sampling interval median chart[J]. Industrial Engineering and Management,2017,22(4):62-67.
[28] 顾丽君,唐庆国. 未知协方差条件下的VSSI T~2控制图的经济性设计[J]. 统计与决策,2018,34(10):183-185.
GU Lijun,TANG Qingguo. Economic design of VSSI T2 control chart with unknown covariance[J]. Statistics & Decision,2018,34(34):183-185.
[29] 杨铭,宋明顺,方兴华. 基于经济性原则的控制图构建及仿真[J].统计与决策,2020,36(2):29-33.
YANG Ming,SONG Mingshun,FANG Xinghua. Multivariate time series similarity measure for dynamictime warping of adaptive cost[J]. Statistics & Decision,2020,36(2):29-33.
[30] 宋明顺,杨铭,方兴华. 基于最大熵分布的控制图改进与评价研究[J]. 中国管理科学,2019,27(12):208-216.
SONG Mingshun,YANG Ming,FANG Xinghua. Improved control charts based on maximum enteopy and their evaluations[J]. Chinese Journal of Management Science,2019,27(12):208-216.
[31] 王海宇,乔百豪,瞿博阳. 基于APL的EWMA控制图经济统计优化设计[J]. 运筹与管理,2020,29(2):19-27.
WANG Haiyu,QIAO Baihao,QU Boyang. Economic-statistical design of EWMA control chart based on APL[J]. Operations Research and Management Science,2020,29(2):19-27.
[32] 王海宇,瞿博阳,乔百豪. 考虑监测成本和效率的累积和控制图经济统计多目标优化设计[J]. 数理统计与管理:2021,40(5):761-770.
WANG Haiyu,QU Boyang,QIAO Baihao. Economic- statistical multi-objective design of CUSUM chart considering monitoring cost and efficiency[J]. Journal of Applied Statisties and Management,2021,40(5):761-770.
[33] 陈克强,刘伟军,姜兴宇,等. 面向多品种小批量制造过程的关键工序识别与聚类分析方法[J]. 计算机集成制造系统,2022,28(3):812-825.
CHEN Keqiang,LIU Weijun,JIANG Xingyu,et al. Method of key process identification and cluster analysis in multi-variety and small-batch manufacturing process[J]. Computer Integrated Manufacturing,2022,28(3):812-825.