数据驱动的离散制造系统性能退化机理建模与预测控制方法研究

doi:10.3901/JME.2024.16.400

机械工程学报 ›› 2024, Vol. 60 ›› Issue (16): 400-411.doi: 10.3901/JME.2024.16.400

扫码分享

数据驱动的离散制造系统性能退化机理建模与预测控制方法研究

王文波^1,2, 张映锋², 顾寄南¹, 张耿², 完严¹

1. 江苏大学机械工程学院镇江 212013;
2. 西北工业大学工业工程与智能制造工信部重点实验室西安 710072

收稿日期:2023-11-06 修回日期:2024-04-08 出版日期:2024-08-20 发布日期:2024-10-21
作者简介:王文波,男,1991年出生,博士,讲师。主要研究方向为智能制造系统优化、预测性生产控制。E-mail:wangwb@ujs.edu.cn
张映锋(通信作者),男,1979年出生,博士,教授,博士研究生导师。主要研究方向为物联制造系统、产品服务系统与绿色制造、制造系统智能化。E-mail:zhangyf@nwpu.edu.cn
顾寄南,男,1964年出生,博士,教授,博士研究生导师。主要研究方向为智能制造系统优化、智能机器人。E-mail:gjnan@ujs.edu.cn
张耿,男,1991年出生,博士,副教授。主要研究方向为云制造、智能制造服务协同优化。E-mail:geng.zhang@nwpu.edu.cn
完严,男,2001年出生。主要研究方向为智能制造系统,边云协同数据分析。E-mail:1805922513@qq.com
基金资助:
国家自然科学基金资助项目(52105516)。

Research on Data-driven Performance Degradation Mechanism Modelling and Predictive Control Method for Discrete Manufacturing System

WANG Wenbo^1,2, ZHANG Yingfeng², GU Jinan¹, ZHANG Geng², WAN Yan¹

1. School of Mechanical Engineering, Jiangsu University, Zhenjiang 212013;
2. Key Laboratory of Industrial Engineering and Intelligent Manufacturing, Ministry of Industry and Information Technology, Northwestern Polytechnical University, Xi'an 710072

Received:2023-11-06 Revised:2024-04-08 Online:2024-08-20 Published:2024-10-21

摘要/Abstract

摘要： 异常事件的主动感知与优化控制是制造系统可靠运行的关键。针对离散制造系统中生产环境不确定性强、关键性能退化规律复杂和数据云端融合时间长等带来的异常识别滞后与优化响应困难的问题，提出一种数据驱动的离散制造系统性能退化机理建模与预测控制方法体系。通过对基于边云协同的离散制造系统智能环境配置与性能提取、基于跨时空状态数据的制造系统关键性能退化机理建模、融合运维知识与预测性能的制造异常预警与主动优化控制等关键技术的深入分析和研究，建立一种具有边云协同交互决策能力的智能制造系统，并实现异常事件事前预警与主动自适应优化决策。所提体系架构和关键技术可以为下一代“智能工厂”的预测性控制方案的落地应用提供重要基础理论和技术支撑。

关键词: 智能制造, 自适应优化, 离散制造系统, 性能退化, 预测控制

Abstract: The active sensing and optimal control of abnormal events are the core issues to ensure the reliable operation of discrete manufacturing system. For a discrete manufacturing system, many uncertain factors exist in the production system, the degradation patterns of production performance are hard to describe, and the cloud-based data fusion methods consume a long time, as a result, the detection of abnormal events often delays and the optimal decisions are hard to find. To meet these requirements, it is provided a data-driven production performance degradation mechanism and predictive control method for discrete manufacturing system. Firstly, the industrial Internet of Things and Cyber Physical System technologies are combined to establish a cloud-edge cooperation environment and extract the key production performance information. Secondly, the degradation mechanism of production performance is modelled based on the fusion of spatial-temporal manufacturing data. Thirdly, the operational knowledge and predicted performance of manufacturing system will be combined to present an exception early-warning and proactively optimal control method. Then, the capacity of cloud-edge cooperation, early-warning of production exceptions and predictive and optimal control of smart discrete manufacturing system can be achieved. The proposed strategy, method and model provide the important support and technical reference for the predictive control of next generation smart factory.

Key words: smart manufacturing, self-adaptive optimization, discrete manufacturing system, performance degradation, predictive control

中图分类号:

TP39
TP301

王文波, 张映锋, 顾寄南, 张耿, 完严. 数据驱动的离散制造系统性能退化机理建模与预测控制方法研究[J]. 机械工程学报, 2024, 60(16): 400-411.

WANG Wenbo, ZHANG Yingfeng, GU Jinan, ZHANG Geng, WAN Yan. Research on Data-driven Performance Degradation Mechanism Modelling and Predictive Control Method for Discrete Manufacturing System[J]. Journal of Mechanical Engineering, 2024, 60(16): 400-411.

参考文献

[1] 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.
[2] GUO Z,ZHANG Y,ZHAO X,et al. CPS-based self-adaptive collaborative control for smart production-logistics systems[J]. IEEE Transactions on Cybernetics,2020,51(1):188-198.
[3] 李浩,王昊琪,程颖,等. 数据驱动的复杂产品智能服务技术与应用[J]. 中国机械工程,2020,31(7):757-772. LI Hao,WANG Haoqi,CHENG Ying,et al. Technology and application of data-driven intelligent services for complex products[J]. China Mechanical Engineering,2020,31(7),757-772.
[4] WANG W,ZHANG Y,GU J,et al. A proactive manufacturing resources assignment method based on production performance prediction for the smart factory[J]. IEEE Transactions on Industrial Informatics,2022,18(1):46-55.
[5] ZHANG Y,ZHANG G,WANG J,et al. Real-time information capturing and integration framework of the internet of manufacturing things[J]. International Journal of Computer Integrated Manufacturing,2015,28(8):811-822.
[6] WANG H,GONG Q,WANG S. Information processing structures and decision-making delays in MRP and JIT[J]. International Journal of Production Economics,2017,188:41-49.
[7] LI T,SHI T,TANG Z,et al. Real-time tool wear monitoring using thin-film thermocouple[J]. Journal of Materials Processing Technology,2021,288(116901):1-8.
[8] ZHANG J,DENG C Y,ZHENG P,et al. Development of an edge computing-based cyber-physical machine tool[J]. Robotics and Computer-Integrated Manufacturing,2021,67(102042):1-12.
[9] SAEZ M,MATURANA F,BARTON K. Real-time manufacturing machine and system performance monitoring using internet of things[J]. IEEE Transactions on Automation Science and Engineering,2018,15(4):1735-1748.
[10] ZOU J,CHANG Q,ARINEZ J,et al. Production performance prognostics through model-based analytical method and recent-weighted stochastic approximation method[J]. Journal of Manufacturing Systems,2018,47:107-114.
[11] HU H,LIU Y. Supervisor synthesis and performance improvements for automated manufacturing systems using petri nets[J]. IEEE Transactions on Industrial Informatics,2015,11(2):450-458.
[12] JIA Z,ZHAO K,ZHANG Y,et al. Real-time performance evaluation and improvement of assembly systems with Bernoulli machines and finite production runs[J]. International Journal of Production Research,2019,57(18):5749-5766.
[13] 卫炳坤,王庆锋,刘家赫,等. 基于动态长短期记忆网络的设备性能退化预测方法[J]. 北京化工大学学报(自然科学版),2020,47(6):92-99. WEI Bingkun,WANG Qingfeng,LIU Jiahe,et al. An equipment performance degradation prediction method based on a dynamic long-short-term memory network[J]. Journal of Beijing University of Chemical Technology (Natural Science),2020,47(6):92-99.
[14] WANG Y,XU J,SUN Y. Tool orientation adjustment for improving the kinematics performance of 5-axis ball-end machining via CPM method[J]. Robotics and Computer- Integrated Manufacturing,2021,68(102070):1-12.
[15] XU L,HUANG C,LI C,et al. An improved case-based reasoning method and its application in estimation of surface quality toward intelligent machining[J]. Journal of Intelligent Manufacturing,2021,32(1):313-327.
[16] 陈超逸,鲁娟,陈楷,等. 车削表面粗糙度解析模型与DDQN-SVR预测模型研究[J]. 机械工程学报,2021,57(13):262-272. CHEN Chaoyi,LU Juan,CHEN Kai,et al. Research on analytical model and DDQN-SVR prediction model of turning surface roughness[J]. Journal of Mechanical Engineering,2021,57(13):262-272.
[17] YE Z,YANG H,CAI Z,et al. Performance evaluation of serial-parallel manufacturing systems based on the impact of heterogeneous feedstocks on machine degradation[J]. Reliability Engineering & System Safety,2021,207(107319):1-11.
[18] 丁华,杨亮亮,杨兆建,等. 数字孪生与深度学习融合驱动的采煤机健康状态预测[J]. 中国机械工程,2020,31(7):815-823. DING Hua,YANG Liangliang,YANG Zhaojian,et al. Health prediction of shearers driven by digital twin and deep learning[J]. China Mechanical Engineering. 2020,31(7):815-823.
[19] WANG J,ZHANG J,WANG X. A data driven cycle time prediction with feature selection in a semiconductor wafer fabrication system[J]. IEEE Transactions on Semiconductor Manufacturing,2018,31(1):173-182.
[20] 王庆锋,卫炳坤,刘家赫,等. 一种数据驱动的旋转机械早期故障检测模型构建和应用研究[J]. 机械工程学报,2020,56(16):22-32. WANG Qingfeng,WEI Bingkun,LIU Jiahe,et al. Research on construction and application of data-driven incipient fault detection model for rotating machinery[J]. Journal of Mechanical Engineering,2020,56(16):22-32.
[21] 刘君强,谢吉伟. 基于性能退化数据融合的航空发动机剩余寿命预测方法[J]. 武汉理工大学学报,2020,44(6):994-998,1003. LIU Junqiang,XIE Jiwei. Remaining useful life prediction method of aero engine based on data-fusion of performance degradation[J]. Journal of Wuhan University of Technology,2020,44(6):994-998,1003.
[22] 李乃鹏,蔡潇,雷亚国,等. 一种融合多传感器数据的数模联动机械剩余寿命预测方法[J]. 机械工程学报,2021,57(20):29-37,46. LI Naipeng,CAI Xiao,LEI Yaguo,et al. A model-data-fusion remaining useful life prediction method with multi-sensor fusion for machinery[J]. Journal of Mechanical Engineering,2021,57(20):29-37,46.
[23] HE Y,GU C,CHEN Z,et al. Integrated predictive maintenance strategy for manufacturing systems by combining quality control and mission reliability analysis[J],International Journal of Production Research,2017,55(19):5841-5862.
[24] WAN J,TANG S,LI D,et al. A manufacturing big data solution for active preventive maintenance[J]. IEEE Transactions on Industrial Informatics,2017,13(4):2039-2047.
[25] ZHAO Z,WANG S,WANG Z,et al. Surface roughness stabilization method based on digital twin-driven machining parameters self-adaption adjustment:A case study in five axis machining[J]. Journal of Intelligent Manufacturing,2022,33:943-952.
[26] ADAMSON G,WANG L,MOORE P. Feature-based control and information framework for adaptive and distributed manufacturing in cyber physical systems[J]. Journal of Manufacturing Systems,2017,43:305-315.
[27] BILBERG A,MALIK A. Digital twin driven human robot collaborative assembly[J]. CIRP Annals-Manufacturing Technology,2019,68(1):499-502.
[28] 张映锋,郭振刚,钱成,等. 基于过程感知的底层制造资源智能化建模及其自适应协同优化方法研究[J]. 机械工程学报,2018,54(16):1-10. ZHANG Yingfeng,GUO Zhengang,QIAN Chen,et al. Investigation on process aware based intelligent modeling of bottom layer manufacturing resources and self-adaptive collaborative optimization methodology[J]. Journal of Mechanical Engineering,2018,54(16):1-10.

数据驱动的离散制造系统性能退化机理建模与预测控制方法研究

Research on Data-driven Performance Degradation Mechanism Modelling and Predictive Control Method for Discrete Manufacturing System

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张党, 赵永宣, 王振军, 张映锋. 数据-知识混合驱动的离散制造系统智能控制体系构架研究[J]. 机械工程学报, 2024, 60(6): 1-10,20.
[2]	狄子钧, 袁东风, 李东阳, 梁道君, 周晓天, 信苗苗, 曹凤, 雷腾飞. 基于多尺度-高效通道注意力网络的刀具故障诊断方法[J]. 机械工程学报, 2024, 60(6): 82-90.
[3]	王跃飞, 王超, 许于涛, 孙睿, 肖锴, 王凯林. 边-云协同下智能制造单元作业的数字孪生任务调度方法[J]. 机械工程学报, 2024, 60(6): 137-152.
[4]	刘思远, 艾超, 郁春嵩, 张伟哲, 陈文婷, 康伟. 基于深度信念网络多参数智能融合的滑靴副性能退化状态评估方法[J]. 机械工程学报, 2024, 60(4): 178-188.
[5]	苏建涛, 董绍华, 朱诗敏. 多目标混合流水车间机器故障重调度问题研究[J]. 机械工程学报, 2024, 60(4): 438-448.
[6]	郭景华, 李文昌, 王班, 王靖瑶. 基于深度强化学习的网联混合动力汽车队列控制[J]. 机械工程学报, 2024, 60(2): 262-271.
[7]	姚建均, 张宜坤, 柯运, 钱琛, 王超. 基于模型预测控制的机器人姿态控制策略研究[J]. 机械工程学报, 2024, 60(19): 88-100.
[8]	王耀南, 谢核, 邓晶丹, 毛建旭, 李文龙, 张辉. 智能制造测量机器人关键技术研究综述[J]. 机械工程学报, 2024, 60(16): 1-18.
[9]	李昊, 宾洋, 胡杰, 岳肖, 金庭安, 张凯. 无偏显式模型预测控制及其在质子交换膜燃料电池净输出功率跟踪中的应用[J]. 机械工程学报, 2024, 60(14): 282-297.
[10]	郄天琪, 王伟达, 杨超, 李颖, 项昌乐. 面向分体式飞行汽车自主对接的自动驾驶底盘运动规划方法研究[J]. 机械工程学报, 2024, 60(10): 235-244.
[11]	刘聪, 刘辉, 韩立金, 聂士达. 基于学习型滑模预测控制的无人驾驶车辆非结构化环境轨迹跟踪及稳定性控制[J]. 机械工程学报, 2024, 60(10): 399-412.
[12]	张寒, 刘开华, 王春燕, 赵万忠, 栾众楷. 四轮分布式线控转向系统稳定与协调控制研究[J]. 机械工程学报, 2024, 60(10): 425-438.
[13]	李兵兵, 庄伟超, 刘昊吉, 张昊, 殷国栋, 张建润. 基于自学习型MPC的网联电动汽车生态驾驶控制策略研究[J]. 机械工程学报, 2024, 60(10): 453-462.
[14]	郑湃, 李成熙, 殷悦, 张荣, 鲍劲松, 王柏村, 谢海波, 王力翚. 增强现实辅助的互认知人机安全交互系统[J]. 机械工程学报, 2023, 59(6): 173-184.
[15]	周健, 郑联语, 樊伟, 张学鑫, 曹彦生. 工业机器人定位误差在线自适应补偿[J]. 机械工程学报, 2023, 59(5): 53-66.