Initiative Scheduling Method Triggered by Production Trend Prediction
-
摘要: 为应对自适应制造需求由被动式调度向主动式调度的转变,提出一种以生产趋势预测为基础的主动式调度。该方法首先构建了实时状态模型,从制造资源、制造资源组合以及生产任务3个层面对生产过程的历史信息和实时状态进行建模,形成了具有时间序列的生产过程状态信息;针对生产过程的不确定性特征,采用贝叶斯网络推理方法,以生产过程状态信息作为输入,获取生产趋势的预测结果;将获取的异常趋势作为主动式调度的触发条件,通过扩展蒙特卡洛树搜索算法,利用其序贯决策能力生成以生产趋势预测为基础的主动式调度方案,从而实现生产过程的自适应制造。将提出的方法应用在某航天机加车间的实时生产过程调度中,验证了方法的有效性。Abstract: To satisfy the requirements for transition from passive scheduling to active scheduling, an active scheduling method based on production trend prediction was proposed. Its real-time model was established first. For manufacturing resources, their combination and production task, for historic information and real time state, for time series process information on production; for the uncertainty feature of production processes, the Bayesian network inference method was adopted, using the state information on production processes as input to infer the production trend and obtain the abnormal production trend as trigger conditions of active scheduling. By extending the Monte-Carlo tree search algorithm and using its sequential decision-making capacity, the initiative scheduling scheme is generated based on production trend prediction, and adaptive manufacturing is realized. Finally, the active scheduling method was applied to the real time production process analysis of aerospace machining job shop scheduling, thus verifying its effectiveness.
-
Key words:
- real-time state /
- production trend prediction /
- active scheduling
-
表 1 某航天机加车间实例数据
任务 工序 机床 ResM1 ResM2 ResM3 ResM4 ResM5 ResM6 1 1, 12;2, 14 1, 18;1, 20 1, 18;2, 22 2 1, 10; 2, 8 1, 6;2, 8 2, 10 Task1 3 1, 8;2, 10 1, 10;2, 13 1, 12;2, 10 4 1, 14;2, 17 1, 18;2, 16 1, 16;1, 18 5 1, 8;2, 11 1, 10;2, 12 1, 13;2, 10 1 1, 18;2, 16 1, 8;2, 15 1, 14;2, 16 2 1, 16;2, 18 1, 9;2, 16 1, 10;2, 15 Task2 3 1, 7;2, 13 1, 14;2, 12 1, 14;2, 16 4 1, 8;2, 11 1, 10;2, 12 1, 13;2, 10 5 1, 20 1, 16;2, 18 1, 18;2, 20 1 1, 18 1, 8 2, 7 1, 6;2, 10 2 1, 7;2, 10 1, 10;2, 8 1, 14;2, 10 Task3 3 1, 10;2, 7 1, 10;2, 15 1, 15;2, 14 4 1, 10;2, 13 2, 18 1, 16 1, 10 5 1, 20;2, 18 1, 16;2, 12 1, 20;2, 18 1, 15;2, 18 1 1, 14;2, 8 1, 10;2, 16 1, 18;2, 15 1, 16;2, 10 Task4 2 1, 12;2, 16 1, 18;2, 15 1, 18;2, 20 1, 16;2, 8 3 1, 16;2, 18 1, 16;2, 15 1, 20;2, 18 1, 10;2, 16 4 1, 20;2, 18 1, 16;2, 12 1, 20;2, 14 1, 15;2, 18 1 1, 18;2, 16 1, 8;2, 15 1, 14;2, 16 Task5 2 1, 16;2, 18 1, 9;2, 16 1, 10;2, 15 3 1, 7;2, 13 1, 14;2, 10 1, 14;2, 16 1 1, 8;2, 7 1, 8;2, 6 1, 6;1, 8 Task6 2 1, 8;2, 11 1, 10;2, 12 1, 13;2, 10 3 1, 20;2, 18 1, 16;2, 12 1, 10;2, 16 1, 12;2, 14 4 1, 14;2, 8 1, 20;2, 14 1, 18;2, 15 1, 16;2, 10 表 2 镗铣床实时加工数据
组号 切削速度/ (m·min-1) 转速/ (r·min-1) 进给量/ (mm·r-1) 背吃刀量/ mm 加工后孔径/mm 表面粗糙度 加工前刀具长度/mm 加工前刀具直径/mm 加工后刀具长度/mm 加工后刀具直径/mm 刀具磨损/ mm 1 140 766 0.08 0.1 58 0.8 130.91 28.146 130.887 28.15 0.036 2 140 766 0.08 0.1 58.2 0.8 130.91 28.148 130.914 28.153 0.052 3 140 766 0.08 0.1 58.4 1.2 130.91 28.15 130.897 28.153 0.068 27 140 651 0.12 0.3 68.4 2.8 130.96 33.088 130.947 33.091 0.227 28 140 646 0.12 0.3 69 2.8 130.93 33.394 130.92 33.412 0.253 30 140 640 0.12 0.3 69.6 3.2 131 33.685 130.967 33.692 0.278 -
[1] 王喜文.中国制造2025解读[M].北京:机械工业出版社, 2015Wang X W. Demystifying made in China 2025[M]. Beijing:China Machine Press, 2015(in Chinese) [2] Zhang J, Ding G F, Zou Y S, et al. Review of job shop scheduling research and its new perspectives under Industry 4.0[J]. Journal of Intelligent Manufacturing, 2017, (3):1-22 doi: 10.1007/s10845-017-1350-2 [3] Li H, Ji Y J, Luo G F, et al. A modular structure data modeling method for generalized products[J]. International Journal of Advanced Manufacturing Technology, 2016, 84(1-4):197-212 doi: 10.1007/s00170-015-7815-6 [4] Wang J Q, Fan G Q, Yan F Y, et al. Research on initiative scheduling mode for a physical internet-based manufacturing system[J]. International Journal of Advanced Manufacturing Technology, 2016, 84(1-4):47-58 doi: 10.1007/s00170-015-7915-3 [5] 彭建刚, 刘明周, 张铭鑫, 等.多目标柔性作业车间调度算法研究综述[J].中国机械工程, 2014, 25(23):3244-3254 doi: 10.3969/j.issn.1004-132X.2014.23.023Peng J G, Liu M Z, Zhang M X, et al. Review on scheduling algorithms for MOFJSP[J]. China Mechanical Engineering, 2014, 25(23):3244-3254(in Chinese) doi: 10.3969/j.issn.1004-132X.2014.23.023 [6] Li J Q, Pan Q K. Chemical-reaction optimization for flexible job-shop scheduling problems with maintenance activity[J]. Applied Soft Computing, 2012, 12(9):2896-2912 doi: 10.1016/j.asoc.2012.04.012 [7] 汪双喜, 张超勇, 刘琼, 等.不同再调度周期下的柔性作业车间动态调度[J].计算机集成制造系统, 2014, 20(10):2470-2478 http://d.old.wanfangdata.com.cn/Periodical/jsjjczzxt201410015Wang S X, Zhang C Y, Liu Q, et al. Flexible job shop dynamic scheduling under different reschedule periods[J]. Computer Integrated Manufacturing Systems, 2014, 20(10):2470-2478(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jsjjczzxt201410015 [8] 陶辛阳, 夏唐斌, 奚立峰.基于健康指数的预防性维护与多目标生产调度联合优化建模[J].上海交通大学学报, 2014, 48(8):1170-1174 http://d.old.wanfangdata.com.cn/Periodical/shjtdxxb201408020Tao X Y, Xia T B, Xi L F. Health-index-based joint optimization of preventive maintenance and multi-attribute production scheduling[J]. Journal of Shanghai Jiaotong University, 2014, 48(8):1170-1174(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/shjtdxxb201408020 [9] 肖世昌, 孙树栋, 杨宏安.加工时间随机可控Job Shop前摄调度研究[J].西北工业大学学报, 2014, 32(6):929-936 doi: 10.3969/j.issn.1000-2758.2014.06.019Xiao S C, Sun S D, Yang H A. Proactive scheduling research on Job Shop with stochastically controllable processing times[J]. Journal of Northwestern Polytechnical University, 2014, 32(6):929-936(in Chinese) doi: 10.3969/j.issn.1000-2758.2014.06.019 [10] Cui W W, Lu Z Q, Li C, et al. A proactive approach to solve integrated production scheduling and maintenance planning problem in flow shops[J]. Computers & Industrial Engineering, 2018, 115:342-353 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=bc5e9e1df578e3eed4c2dccad06021a2 [11] 侯瑞春, 丁香乾, 陶冶, 等.制造物联及相关技术架构研究[J].计算机集成制造系统, 2014, 20(1):11-20 http://d.old.wanfangdata.com.cn/Periodical/jsjjczzxt201401002Hou R C, Ding X Q, Tao Y, et al. Internet of manufacturing things and relevant technical architecture[J]. Computer Integrated Manufacturing Systems, 2014, 20(1):11-20(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jsjjczzxt201401002 [12] 贺长鹏, 郑宇, 王丽亚, 等.面向离散制造过程的RFID应用研究综述[J].计算机集成制造系统, 2014, 20(5):1160-1170 http://d.old.wanfangdata.com.cn/Periodical/jsjjczzxt201405019He C P, Zheng Y, Wang L Y, et al. RFID application research for discrete manufacturing[J]. Computer Integrated Manufacturing Systems, 2014, 20(5):1160-1170(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jsjjczzxt201405019 [13] 张映锋, 赵曦滨, 孙树栋, 等.一种基于物联技术的制造执行系统实现方法与关键技术[J].计算机集成制造系统, 2012, 18(12):2634-2642 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=QK201206136478Zhang Y F, Zhao X B, Sun S D, et al. Implementing method and key technologies for IoT-based manufacturing execution system[J]. Computer Integrated Manufacturing Systems, 2012, 18(12):2634-2642(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=QK201206136478 [14] García-Valls M, Perez-Palacin D, Mirandola R. Time-sensitive adaptation in CPS through run-time configuration generation and verification[C]//2014 IEEE 38th Annual Computer Software and Applications Conference. Vasteras, Sweden: IEEE, 2014: 332-337 [15] Yun S, Park J H, Kim W T. Data-centric middleware based digital twin platform for dependable cyber-physical systems[C]//2017 Ninth International Conference on Ubiquitous and Future Networks. Milan, Italy: IEEE, 2017 [16] Chaslot G M J B C. Monte-carlo tree search[D]. Holland: Maastricht University, 2010 [17] Yoshida S, Ishihara M, Miyazaki T, et al. Application of Monte-Carlo tree search in a fighting game AI[C]//2016 IEEE 5th Global Conference on Consumer Electronics. Kyoto, Japan: IEEE, 2016: 1-2 [18] Wu T Y, Wu I C, Liang C C. Multi-objective flexible job shop scheduling problem based on monte-carlo tree search[C]//2013 Conference on Technologies and Applications of Artificial Intelligence. Taipei, China: IEEE, 2013: 73-78 [19] Lu C L, Chiu S Y, Wu J, et al. Dynamic Monte-Carlo tree search algorithm for multi-objective flexible job-shop scheduling problem[J]. Applied Mathematics & Information Sciences, 2016, 10(4):1531-1539 http://www.naturalspublishing.com/Article.asp?ArtcID=11823 [20] Weber P, Medina-Oliva G, Simon C, et al. Overview on Bayesian networks applications for dependability, risk analysis and maintenance areas[J]. Engineering Applications of Artificial Intelligence, 2012, 25(4):671-682 doi: 10.1016/j.engappai.2010.06.002 [21] 蔡志强, 司书宾, 孙树栋, 等.基于贝叶斯网络的不确定环境装备故障推理模型[J].西北工业大学学报, 2011, 29(4):509-514 doi: 10.3969/j.issn.1000-2758.2011.04.002Cai Z Q, Si S B, Sun S D, et al. Applying BN (Bayesian Network) to establishing a new and effective failure inference model of equipment under uncertainties[J]. Journal of Northwestern Polytechnical University, 2011, 29(4):509-514(in Chinese) doi: 10.3969/j.issn.1000-2758.2011.04.002 [22] Lakehal A, Ramdane A. Fault prediction of induction motor using Bayesian network model[C]//2017 International Conference on Electrical and Information Technologies. Rabat, Morocco: IEEE, 2017: 1-5