大数据驱动的离散制造车间生产过程智能管控方法研究

doi:10.3901/JME.2021.20.277

机械工程学报 ›› 2021, Vol. 57 ›› Issue (20): 277-291.doi: 10.3901/JME.2021.20.277

扫码分享

大数据驱动的离散制造车间生产过程智能管控方法研究

方伟光^1,2, 郭宇¹, 黄少华^1,3, 刘道元¹, 崔世婷¹, 廖文和¹, 洪东跑²

1. 南京航空航天大学航空宇航制造工程系南京 210016;
2. 中国运载火箭技术研究院北京 100076;
3. 清华大学工业工程系北京 100084

收稿日期:2020-06-30 修回日期:2021-04-21 出版日期:2021-10-20 发布日期:2021-12-15
通讯作者: 郭宇(通信作者),男,1971年出生,教授,博士研究生导师。主要研究方向为智能制造技术、制造物联网、制造大数据技术、制造系统仿真与优化。E-mail:guoyu@nuaa.edu.cn
作者简介:方伟光,男,1990年出生,博士。主要研究方向为制造大数据、智能制造技术、车间生产管控。E-mail:fang_weiguang@hotmail.com;黄少华,男,1990年出生,博士后。主要研究方向为智能制造技术、制造物联技术、车间生产管控。E-mail:shaohuah@nuaa.edu.cn;刘道元,男,1995年出生,博士研究生。主要研究方向为制造大数据分析、车间调度。E-mail:l1562773948@163.com;崔世婷,女,1996年出生,硕士研究生。主要研究方向为制造大数据分析、车间生产异常检测。E-mail:1767493582@qq.com;廖文和,男,1965年出生,教授,博士研究生导师。主要研究方向为智能制造技术、微小卫星技术、CAD/CAM、高端机器人装备等。E-mail:cnwho@mail.njust.edu.cn;洪东跑,男,1983年出生,博士,研究员。主要研究方向为装备智能保障体系、装备健康管理和飞行器总体设计。Email:hloving@163.com
基金资助:
国家自然科学基金（52105522）、江苏省自然科学基金（BK20202007）和国防基础科研重点（JCKY2016605B006）资助项目。

Big Data Driven Intelligent Production Control of Discrete Manufacturing Process

FANG Weiguang^1,2, GUO Yu¹, HUANG Shaohua^1,3, LIU Daoyuan¹, CUI Shiting¹, LIAO Wenhe¹, HONG Dongpao²

1. Department of Manufacturing Engineering of Aeronautics & Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 210016;
2. China Academy of Launch Vehicle Technology, Beijing 100076;
3. Department of Industrial Engineering, Tsinghua University, Beijing 100084

Received:2020-06-30 Revised:2021-04-21 Online:2021-10-20 Published:2021-12-15

摘要/Abstract

摘要： 在智能制造背景下，离散制造企业对利用大数据技术提高车间生产管控水平提出了迫切的需求。研究大数据驱动的离散制造车间生产过程智能管控方法，在明确离散制造车间特点与管控需求的基础上，分析了传统方法的局限性和大数据方法的优势，进而提出大数据驱动的离散制造车间生产过程管控总体框架，以制造大数据的"采集-处理-分析-服务"为主线开展研究。在"进度预测-瓶颈发现-异常溯源-智能决策"的生产过程闭环管控机制中，分别提出：基于堆叠稀疏自编码机的生产进度在线预测技术，基于平行门控循环单元的生产瓶颈漂移发现技术，基于密度峰值-模糊C均值的生产异常溯源分析技术和基于多智能体强化学习的生产过程智能决策技术。最后，以某航空企业典型离散制造车间作为对象，对所提出的大数据分析与智能决策方法进行了原型系统开发和应用验证。

关键词: 离散制造车间, 制造大数据, 生产过程管控, 数据分析, 智能决策

Abstract: Under intelligent manufacturing era, there is pressing demands from discrete manufacturing enterprise to utilize big data (BD) technologies for enhancing the level of production management and control (PM&C). The BD driven intelligent PM&C in discrete manufacturing process is studied. Based on the determination of characteristics and demands for PM&C, the architecture of BD driven PM&C is firstly constructed, which the main flow is "collection-processing-analysis-service" of manufacturing BD. Based on the closed-loop mechanism "progress prediction-bottleneck discovery-anomaly tracing-decision making" for PM&C, the key technologies are respectively proposed, which are:"A stacked sparse auto-encoder model for production progress prediction", "The parallel gated recurrent units model for shifting bottleneck discovery", "The density peak-weighted fuzzy C-means method for anomaly tracing" and "The multi-agents reinforcement learning for production decision-making". Finally, an aircraft discrete manufacturing workshop is selected as the application scenario to verify the developed prototype system.

Key words: discrete manufacturing workshop, manufacturing big data, production management and control, data analysis, intelligent decision-making

中图分类号:

TH186
TP391

方伟光, 郭宇, 黄少华, 刘道元, 崔世婷, 廖文和, 洪东跑. 大数据驱动的离散制造车间生产过程智能管控方法研究[J]. 机械工程学报, 2021, 57(20): 277-291.

FANG Weiguang, GUO Yu, HUANG Shaohua, LIU Daoyuan, CUI Shiting, LIAO Wenhe, HONG Dongpao. Big Data Driven Intelligent Production Control of Discrete Manufacturing Process[J]. Journal of Mechanical Engineering, 2021, 57(20): 277-291.

参考文献

[1] 屈挺,张凯,罗浩,等. 物联网驱动的"生产-物流"动态联动机制、系统及案例[J]. 机械工程学报,2015,51(20):36-44. QU Ting,ZHANG Kai,LUO Hao,et al. Internet-of- things based dynamic synchronization of production and logistics:Mechanism,system and case study[J]. Journal of Mechanical Engineering,2015,51(20):36-44.
[2] 黄少华,郭宇,查珊珊,等. 离散车间制造物联网及其关键技术研究与应用综述[J]. 计算机集成制造系统,2019,25(2):284-302. HUANG Shaohua,GUO Yu,ZHA Shanshan,et al. Review on Internet-of-manufacturing-things and key technologies for discrete workshop[J]. Computer Integrated Manufacturing Systems,2019,25(2):284-302.
[3] 张洁,高亮,秦威,等. 大数据驱动的智能车间运行分析与决策方法体系[J]. 计算机集成制造系统,2016,22(5):1220-1228. ZHANG Jie,GAO Liang,QIN Wei,et al. Big-data-driven operational analysis and decision-making methodology in intelligent workshop[J]. Computer Integrated Manufacturing Systems,2016,22(5):1220-1228.
[4] KUSIAK A. Smart manufacturing must embrace big data[J]. Nature,2017,544(7648):23-25.
[5] ROSSIT D,TOHMÉ F,FRUTOS M. A data-driven scheduling approach to smart manufacturing[J]. Journal of Industrial Information Integration,2019,15:69-79.
[6] TAO F,QI Q,LIU A,et al. Data-driven smart manufacturing[J]. Journal of Manufacturing Systems,2018(48):157-169.
[7] 任杉,张映锋,黄彬彬. 生命周期大数据驱动的复杂产品智能制造服务新模式研究[J]. 机械工程学报,2018,54(22):194-203. REN Shan,ZHANG Yingfeng,HUANG Binbin. New pattern of lifecycle big-data-driven smart manufacturing service for complex product[J]. Journal of Mechanical Engineering,2018,54(22):194-203.
[8] ZHANG Y,REN S,LIU Y,et al. A big data analytics architecture for cleaner manufacturing and maintenance processes of complex products[J]. Journal of Cleaner Production,2017,142:626-641.
[9] MORARIU C,MORARIU O,RILEANU S,et al. Machine learning for predictive scheduling and resource allocation in large scale manufacturing systems[J]. Computers in Industry,2020,120:103244.
[10] 汤洪涛,费永辉,陈青丰,等. 基于工业大数据的柔性作业车间动态调度[J]. 计算机集成制造系统,2020,26(9):2497-2510. TANG Hongtao,FEI Yonghui,CHEN Qingfeng,et al. Flexible job shop dynamic scheduling based on industrial big data[J]. Computer Integrated Manufacturing System,2020,26(9):2497-2510.
[11] ZHONG R Y,HUANG G Q,LAN S,et al. A big data approach for logistics trajectory discovery from RFID-enabled production data[J]. International Journal of Production Economics,2015,165:260-272.
[12] FANG W G,GUO Y,LIAO W H,et al. The spatio-temporal modeling and integration of manufacturing big data in job shop:An ontology -based approach[C/CD]//2020 IEEE International Conference on Industrial Engineering and Applications (ICIEA),Bangkok,2020.
[13] LIU X,QI H,LI K,et al. Sampling bloom filter-based detection of unknown RFID tags[J]. IEEE Transactions on Communications,2015,63(4):1432-1442.
[14] WANG J L,ZHANG J. Big data analytics for forecasting cycle time in semiconductor wafer fabrication system[J]. International Journal of Production Research,2016,54(23):7231-7244.
[15] WANG C,JIANG P Y. Deep neural networks based order completion time prediction by using real-time job shop RFID data[J]. Journal of Intelligent Manufacturing,2019,30(3):1303-1318.
[16] 刘道元,郭宇,黄少华,等. 一种面向订单剩余完工时间预测的SOM-FWFCM特征选择算法[J]. 中国机械工程,2021(9):1073-1079. LIU Daoyuan,GUO Yu,HUANG Shaohua,et al. A SOM-FWFCM based feature selection algorithm for order remaining completion time prediction[J]. China Mechanical Engineering,2021(9):1073-1079.
[17] 汪俊亮,张洁. 大数据驱动的晶圆工期预测关键参数识别方法[J]. 机械工程学报,2018,54(23):185-191. WANG Junliang,ZHANG Jie. Big data driven key factor identification for cycle-time forecasting of wafer lots in semiconductor wafer fabrication system[J]. Journal of Mechanical Engineering,2018,54(23):185-191.
[18] HUANG S H,GUO Y,LIU D Y,et al. A two-stage transfer learning-based deep learning approach for production progress prediction in IoT-enabled manufacturing[J]. IEEE Internet of Things Journal,2019,6(6):10627-10638.
[19] FANG W G,GUO Y,LIAO W H,et al. Big data driven jobs remaining time prediction in discrete manufacturing system:A deep learning-based approach[J]. International Journal of Production Research,2020,58:2751-2766.
[20] LI L. A systematic-theoretic analysis of data-driven throughput bottleneck detection of production systems[J]. Journal of Manufacturing Systems,2018,47:43-52.
[21] LAI X J,SHUI H Y,NI J. A two-layer long short-term memory network for bottleneck prediction in multi-job manufacturing systems[C/CD]//Proceedings of the ASME 201813rd ASME International Manufacturing Science and Engineering Conference,Texas,2018.
[22] SUBRAMANIYAN M,SKOOGH A,SALOMONSSON H,et al. A data-driven algorithm to predict throughput bottlenecks in a production system based on active periods of the machines[J]. Computers & Industrial Engineering,2018,125(11):533-544.
[23] 李晓娟,孙文磊,袁逸萍,等. 扰动环境下作业车间网络多瓶颈识别方法研究[J]. 西安交通大学学报,2016,50(12):64-72. LI Xiaojuan,SUN Wenlei,YUAN Yiping,et al. Multi- bottleneck identification for job-shop network in disturbance environment[J]. Journal of Xi'an Jiaotong University,2016,50(12):64-72.
[24] FANG W G,GUO Y,LIAO W H,et al. A parallel gated recurrent units (P-GRUs) network for the shifting lateness bottleneck prediction in make-to-order production system[J]. Computers & Industrial Engineering,2020,140:106246.
[25] CHIEN C,LIU C M,CHUANG S,et al. Analysing semiconductor manufacturing big data for root cause detection of excursion for yield enhancement[J]. International Journal of Production Research,2017,55(17):5095-5107.
[26] CAO X,LI T J,WANG Q,et al. RFID-based multi-attribute logistics information processing and anomaly mining in production logistics[J]. International Journal of Production Research,2019,57(17):5453-5466.
[27] ZHANG Y,WANG W,WU N,et al. IoT-enabled real-time production performance analysis and exception diagnosis model[J]. IEEE Transactions on Automation Science and Engineering,2016,13(3):1318-1332.
[28] HUANG S,GUO Y,YANG N,et al. A weighted fuzzy c-means clustering method with density peak for anomaly detection in iot-enabled manufacturing process[J]. Journal of Intelligent Manufacturing,2020,40(5):1-8.
[29] 吕盛坪,乔立红. 工艺规划与车间调度及两者集成的研究现状和发展趋势[J]. 计算机集成制造系统,2014,20(2):290-300. LÜ Shengping,QIAO Lihong. Current status and developing trend of process planning and Job Shop scheduling[J]. Computer Integrated Manufacturing Systems,2014,20(2):290-300.
[30] ZHONG R Y,HUANG G Q,LAN S,et al. A two-level advanced production planning and scheduling model for RFID-enabled ubiquitous manufacturing[J]. Advanced Engineering Informatics,2015,29(4):799-812.
[31] JI W,WANG L. Big data analytics based fault prediction for shop floor scheduling[J]. Journal of Manufacturing Systems,2017,43:187-194.
[32] WANG C,JIANG P. Manifold learning based rescheduling decision mechanism for recessive disturbances in RFID-driven job shops[J]. Journal of Intelligent Manufacturing,2018,29(7):1485-1500.

大数据驱动的离散制造车间生产过程智能管控方法研究

Big Data Driven Intelligent Production Control of Discrete Manufacturing Process

PDF

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]	张超, 周光辉, 李晶晶, 魏智博, 秦天宇. 面向航空复杂零件智能工艺规划的孪生工艺模型构建与应用研究[J]. 机械工程学报, 2024, 60(6): 32-43.
[2]	周亚勤, 肖蒙, 吕志军, 汪俊亮, 张洁. 基于DQN算法的考虑AGV小车搬运的离散制造车间调度方法[J]. 机械工程学报, 2024, 60(18): 338-348.
[3]	邓朝晖, 李重阳, 葛吉民, 刘涛. 典型零件磨削加工工艺智能决策系统[J]. 机械工程学报, 2023, 59(12): 126-138.
[4]	华丰, 王亚森, 金骏阳, 袁烨. 一种数据隐私保护下多方无损线性模型学习方法[J]. 机械工程学报, 2023, 59(12): 17-27.
[5]	汪俊亮, 高鹏捷, 张洁, 王力翚. 制造大数据分析综述：内涵、方法、应用和趋势[J]. 机械工程学报, 2023, 59(12): 1-16.
[6]	蒋仁言. 两类高度截尾数据及其参数估计问题[J]. 机械工程学报, 2023, 59(10): 374-382.
[7]	张超, 周光辉, 李晶晶, 魏智博, 常丰田. 新一代信息技术赋能的数字孪生制造单元系统关键技术及应用研究[J]. 机械工程学报, 2022, 58(16): 329-343.
[8]	姜生元, 梁杰能, 赖小明, 邓湘金, 庞勇, 张伟伟, 唐钧跃, 全齐全, 彭兢, 张高, 邓宗全. 嫦娥五号月壤剖面钻进取芯状态分析与解译[J]. 机械工程学报, 2022, 58(10): 348-360.
[9]	李宁,余进. 列车能耗测试装置与分析方法研究^*[J]. 电气工程学报, 2020, 15(3): 50-56.
[10]	佘承其, 张照生, 刘鹏, 孙逢春. 大数据分析技术在新能源汽车行业的应用综述——基于新能源汽车运行大数据[J]. 机械工程学报, 2019, 55(20): 3-16.
[11]	黎敏, 谢玄, 陈泽, 杨孟瑶, 杨德斌, 蒋靖. 基于函数型数据分析的半导体生产过程监控[J]. 机械工程学报, 2018, 54(16): 62-69.
[12]	雷亚国, 贾峰, 周昕, 林京. 基于深度学习理论的机械装备大数据健康监测方法[J]. 机械工程学报, 2015, 51(21): 49-56.
[13]	倪敬;项占琴;潘晓弘;吕福在. 管捆成形电液系统自学习粗糙－模糊PID控制研究[J]. , 2006, 42(10): 224-228.