基于特征选择和SSA-LSTM的车间订单剩余完工时间预测

doi:10.3901/JME.2024.20.388

机械工程学报 ›› 2024, Vol. 60 ›› Issue (20): 388-402.doi: 10.3901/JME.2024.20.388

扫码分享

基于特征选择和SSA-LSTM的车间订单剩余完工时间预测

朱海华¹, 王健杰¹, 李霏², 刘长春¹, 蔡祺祥¹

1. 南京航空航天大学机电学院南京 210016;
2. 北京电子工程总体研究所北京 100854

收稿日期:2023-10-27 修回日期:2024-05-09 出版日期:2024-10-20 发布日期:2024-11-30
通讯作者: 朱海华,男,1985年出生,博士,副教授,硕士研究生导师。主要研究方向为网络协同制造、大数据分析。E-mail:h.zhu@nuaa.edu.cn
作者简介:王健杰,男,1999年出生。主要研究方向为制造车间大数据分析。E-mail:wang126@nuaa.edu.cn;李霏,男,1983年出生,博士。主要研究方向为数字化设计制造。E-mail:leafy777@qq.com;刘长春,男,1995年出生,博士。主要研究方向为增强现实、物联制造车间的智能运维和工业大数据。E-mail:651979759@qq.com;蔡祺祥,男,1984年出生,博士。主要研究方向为智能制造系统。E-mail:cqx@nuaa.edu.cn
基金资助:
国家重点研发计划(2021YFB1716304);中央高校基本科研基金(NT2021021)和成飞-南航“智汇蓝天”工程实践计划六期(CF202206)资助项目。

Workshop Order Remaining Completion Time Prediction Based on the Feature Selection and SSA-LSTM

ZHU Haihua¹, WANG Jianjie¹, LI Fei², LIU Changchun¹, CAI Qixiang¹

1. College of Mechanical &Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016;
2. Beijing Institute of Electronic System Engineering, Beijing 100854

Received:2023-10-27 Revised:2024-05-09 Online:2024-10-20 Published:2024-11-30

摘要/Abstract

摘要： 客户多变的需求和激烈的市场竞争使得车间产品生产种类不断增加、批量不断减小、交货期不断缩短，导致业务流程和制造系统环境愈发复杂与不稳定，对车间生产管控能力提出了更高的要求。订单剩余完工时间(Order remaining completion time,ORCT)精准预测可以及时发现生产计划交期波动，为后续优化车间生产调度计划、改进工艺流程提供判断依据。针对传统数据分析方法在复杂制造环境下大规模制造数据利用分析能力较弱的问题，提出一种大数据驱动的车间ORCT预测方法。基于皮尔森相关系数和正则化的特征选择算法从海量的制造数据中挑选出关键数据；设计一种基于改进麻雀搜索算法-长短期记忆神经网络模型和注意力机制的预测方法实现车间ORCT的快速、精准预测，其中的预测模型以长短期记忆神经网络为结构基础，并使用改进麻雀搜索算法对模型的超参数进行优化；最后，以典型机加车间为对象进行实例验证，通过与三种常用预测方法进行对比，试验结果表明所提方法在准确性和效率上均有明显优势。

关键词: 订单剩余完工时间, 数据驱动, 特征选择, 预测模型

Abstract: The ever-changing demands of customers and fierce market competition have led to an increase in the number of products produced in the workshop, a decrease in batch sizes and a shortening of delivery times, which has led to an increasingly complex and unstable business process and manufacturing system environment, placing greater demands on the workshop's production control capabilities. Accurate forecasting of order remaining completion time(ORCT) allows for the timely detection of production schedule fluctuations and provides a basis for subsequent optimisation of the workshop production scheduling plan and process improvements. A big data-driven workshop ORCT prediction method is proposed to address the weak ability of traditional data analysis methods to utilise large-scale, long-time series manufacturing data in the complex manufacturing environment. A feature selection algorithm based on Pearson's correlation coefficient and regularisation is used to select key data from a huge amount of manufacturing data; a prediction method based on the improved sparrow search algorithm-long and short-term memory neural network model and the attention mechanism is designed to achieve fast and accurate prediction of ORCT in the workshop, where the prediction model is supported by the long and short-term memory neural network structure, which is optimised by the improved sparrow search algorithm; finally, a typical machine workshop is used as an example for verification, by comparing three common prediction methods, the experimental results show that the proposed method has obvious advantages in terms of accuracy and efficiency.

Key words: order remaining completion time, data-driven, feature selection, prediction model

中图分类号:

TP183

朱海华, 王健杰, 李霏, 刘长春, 蔡祺祥. 基于特征选择和SSA-LSTM的车间订单剩余完工时间预测[J]. 机械工程学报, 2024, 60(20): 388-402.

ZHU Haihua, WANG Jianjie, LI Fei, LIU Changchun, CAI Qixiang. Workshop Order Remaining Completion Time Prediction Based on the Feature Selection and SSA-LSTM[J]. Journal of Mechanical Engineering, 2024, 60(20): 388-402.

参考文献

[1] YAN X，GU X. Bi-objective no-wait multiproduct multistage product scheduling problem with flexible due dates based on MOIDE-MA[J]. Computers & Operations Research，2022，137：105543.
[2] ZHAI Y，CHENG T C E. Lead-time quotation and hedging coordination in make-to-order supply chain[J]. European Journal of Operational Research，2022，300(2)：449-460.
[3] YIN S，KAYNAK O. Big data for modern industry： Challenges and trends[J]. Proceedings of the IEEE，2015，103(2)：143-146.
[4] CHOUEIRI A C，SATO D M V，SCALABRIN E E，et al. An extended model for remaining time prediction in manufacturing systems using process mining[J]. Journal of Manufacturing Systems，2020，56：188-201.
[5] CHANG P C，HSIEH J C，LIAO T W. A case-based reasoning approach for due-date assignment in a wafer fabrication factory[C]// International Conference on Case-Based Reasoning，Springer，Berlin，Heidelberg，2001：648-659.
[6] RAMAMURTHI V，KUHI M E，HIRSCHMAN K D. Analysis of production control methods for semiconductor research and development fabs using simulation[C]// Proceedings of the 2005 Winter Simulation Conference，IEEE，2005：2177-2185.
[7] 邵海东，肖一鸣，颜深. 仿真数据驱动的改进无监督域适应轴承故障诊断[J]. 机械工程学报，2023，59(3)：76-85. SHAO Haidong，XIAO Yiming，YAN Shen. Simulation data-driven enhanced unsupervised domain adaptation[J]. Journal of Mechanical Engineering，2023，59(3)：76-85.
[8] WANG C，JIANG P. 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.
[9] SILVA C，RIBEIRO V，COELHO P，et al. Job shop flow time prediction using neural networks[J]. Procedia Manufacturing，2017，11：1767-1773.
[10] CHANG J，KONG X，YIN L. A novel approach for product makespan prediction in production life cycle[J]. The International Journal of Advanced Manufacturing Technology，2015，80(5)：1433-1448.
[11] HUANG S，GUO Y，LIU D，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.
[12] FANG W，GUO Y，LIAO W，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(9)：2751-2766.
[13] 刘阳，郜志英，周晓敏，等. 工业数据驱动下薄板冷轧颤振的LSTM智能预报[J]. 机械工程学报，2020，56(11)：121-131. LIU Yang，GAO Zhiying，ZHOU Xiaomin，et al. Industrial data-driven intelligent forecast for chatter of cold rolling of thin strip with LSTM recurrent neural network[J]. Journal of Mechanical Engineering，2020，56(11)：121-131.
[14] 高凯，李勋豪，胡林，等. 基于多头注意力的CNN-LSTM的换道意图预测[J]. 机械工程学报，2022，58(22)：369-378. GAO Kai，LI Xunhao，HU Lin，et al. Lane change intention prediction of CNN-LSTM based on multi-head attention[J]. Journal of Mechanical Engineering，2022，58(22)：369-378.
[15] 张朝龙，赵筛筛，何怡刚. 基于信息熵与PSO-LSTM的锂电池组健康状态估计方法[J]. 机械工程学报，2022，58(10)：180-190. ZHANG Chaolong，ZHAO Shaishai，HE Yigang. State-of-health estimate for lithium-ion battery using information entropy and PSO-LSTM[J]. Journal of Mechanical Engineering，2022，58(10)：180-190.
[16] LIU C，ZHU H，TANG D，et al. A transfer learning CNN-LSTM network-based production progress prediction approach in IIoT-enabled manufacturing[J]. International Journal of Production Research，2023，61(12)：4045-4068.
[17] 李贝蕾. 面向汽车装配车间订单剩余完工时间预测方法研究[D]. 合肥：合肥工业大学，2022. LI Beilei. Research on prediction method of order remaining completion time for automobile assembly workshop[D]. Hefei：Hefei University of Technology，2022.
[18] LI C，CHEN Y，SHANG Y. A review of industrial big data for decision making in intelligent manufacturing[J]. Engineering Science and Technology，an International Journal，2022，29：101021.
[19] 崔羽飞，张云勇，张第，等. 基于云边协同的工业互联网实践[J]. 电信科学，2020，36(2)：109-116. CUI Yufei，ZHANG Yunyong，ZHANG Di，et al. Analysis and development suggestions of operators in the field of industrial internet identification analysis system[J]. Telecommunication Science，2020，36(2)：109-116.
[20] QIAN W，XIONG Y，YANG J，et al. Feature selection for label distribution learning via feature similarity and label correlation[J]. Information Sciences，2022，582：38-59.
[21] WANG J，ZHENG P，ZHANG J. Big data analytics for cycle time related feature selection in the semiconductor wafer fabrication system[J]. Computers & Industrial Engineering，2020，143：106362.
[22] WANG J，ZHANG J，WANG X. A data driven cycle time prediction with feature selection in a semiconductor wafer fabrication system[J]. IEEE Trans Semicond Manuf，2018，31(1)：173-182.
[23] 毛柯夫，苑明海，孙超，等. 基于扰动事件的智能车间生产管理系统研究[J]. 制造技术与机床，2022(9)：97-103. MAO Kefu，YUAN Minghai，SUN Chao，et al. Research on intelligent workshop production management system based on disturbance event[J]. Manufacturing Technology & Machine Tool，2022(9)：97-103.
[24] XUE J，SHEN B. A novel swarm intelligence optimization approach：Sparrow search algorithm[J]. Systems Science & Control Engineering，2020，8(1)：22-34.

基于特征选择和SSA-LSTM的车间订单剩余完工时间预测

Workshop Order Remaining Completion Time Prediction Based on the Feature Selection and SSA-LSTM

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]	吴吉展, 魏沛堂, 吴少杰, 刘怀举, 朱才朝. 航空齿轮钢滚动接触疲劳性能预测与表面完整性优化[J]. 机械工程学报, 2024, 60(8): 81-93.
[2]	吕志军, 褚铭, 周亚勤, 肖雷, 李宏亮. 物理模拟与数据驱动混合的Z型立柱片剪切刚度认知预测方法[J]. 机械工程学报, 2024, 60(2): 50-61.
[3]	胡成亮, 苗宏量, 曾凡, 赵震, 汤敏俊, 汤晓峰. 热成形条件下软磁材料的磁感应强度预测模型[J]. 机械工程学报, 2024, 60(2): 132-139,149.
[4]	武骥, 方雷超, 刘兴涛, 陈佳佳, 刘晓剑, 吕帮. 基于特征优化和随机森林算法的锂离子电池SOH估计[J]. 机械工程学报, 2024, 60(12): 335-343.
[5]	谭志朴, 秦国华, 娄维达, 吴竹溪. 基于伯努利分布与混合驱动模型的铣削稳定性高精判断方法[J]. 机械工程学报, 2024, 60(11): 318-331.
[6]	邵海东, 肖一鸣, 颜深. 仿真数据驱动的改进无监督域适应轴承故障诊断[J]. 机械工程学报, 2023, 59(3): 76-85.
[7]	郭江, 杨哲, 张鹏飞, 李琳光, 俞学雯, 潘博. FeCrAl合金化学机械抛光粗糙度预测模型研究[J]. 机械工程学报, 2023, 59(23): 310-319.
[8]	庞晓青, 李佳承, 刘文学, 邓忠伟, 胡晓松. 模型与数据融合的大尺寸快充锂电池分布式温度估计[J]. 机械工程学报, 2023, 59(22): 20-32.
[9]	谷平维, 段彬, 康永哲, 张承慧, 杜春水. 基于随机充电数据的锂离子电池容量在线估计[J]. 机械工程学报, 2023, 59(22): 100-110.
[10]	李敏, 陈涛涛, 鲁森, 杨开明, 朱煜, 胡楚雄. 光刻机超精密运动台数据驱动MIMO定结构前馈控制[J]. 机械工程学报, 2023, 59(21): 99-109.
[11]	谢家乐, 李增超, 王光, 姚天琪. 基于电热耦合效应的18650锂离子电池内外温度预测模型[J]. 机械工程学报, 2023, 59(16): 342-352.
[12]	胡炳涛, 冯毅雄, 刘继红, 郭伟, 谭建荣. 面向“互联网+”定制产品的智能适应性设计研究[J]. 机械工程学报, 2023, 59(12): 109-125.
[13]	徐彬翔, 郑林锋, 黄乙恒, 肖志能, 王新月. 基于改进最小二乘支持向量机的锂离子电池健康状态快速估计方法^*[J]. 电气工程学报, 2022, 17(4): 11-19.
[14]	杨淞元, 田勇, 田劲东. 基于iCEEMDAN和迁移学习的锂离子电池SOH估计^*[J]. 电气工程学报, 2022, 17(4): 2-10.
[15]	管寅昕, 杨吉祥, 丁汉. 考虑控制电信号中间量的机床运动控制误差数据驱动建模方法[J]. 机械工程学报, 2022, 58(23): 178-187.