计算机科学 ›› 2025, Vol. 52 ›› Issue (4): 54-63.doi: 10.11896/jsjkx.241000102

• 智能嵌入式系统 • 上一篇    下一篇

基于生成对抗网络的云制造工业服务选择方法

郑秀宝, 李静, 祝铭, 宁莹莹   

  1. 山东理工大学 山东 淄博 255000
  • 收稿日期:2024-10-19 修回日期:2025-02-18 出版日期:2025-04-15 发布日期:2025-04-14
  • 通讯作者: 李静(li_jing@sdut.edu.cn)
  • 作者简介:(22505030025@stumail.sdut.edu.cn)
  • 基金资助:
    国家留学基金管理委员会“促进与加拿大、澳大利亚、新西兰及拉美地区科研合作与高层次人才培养项目”(留美金[2023]21号);教育部高等学校科学研究发展中心中国高校产学研创新基金-新一代信息技术创新项目(2023IT056)

Selection Method for Cloud Manufacturing Industrial Services Based on Generative AdversarialNetworks

ZHENG Xiubao, LI Jing, ZHU Ming, NING Yingying   

  1. School of Computer Science and Technology,Shandong University of Technology,Zibo,Shandong 255000,China
  • Received:2024-10-19 Revised:2025-02-18 Online:2025-04-15 Published:2025-04-14
  • About author:ZHENG Xiubao,born in 1999,postgra-duate,a member of CCF(No.R8865G).His main research interests include intelligent manufacturing,service computing,artificial intelligence and graph neural networks.
    LI Jing,born in 1986,Ph.D,associate professor,graduate supervisor,is a member of CCF(No.C9194M).Her main research interests include edge computing,cloud computing,and ser-vice choices.
  • Supported by:
    China Scholarship Council “Promoting Scientific Research Cooperation and High-level Talent Training Program with Canada,Australia,New Zealand and Latin America”(Liu Mei Jin [2023] No.21) and Research and Development Center of Colleges and Universities of the Ministry of Education,China University Industry-University-Research Innovation Fund-New Generation Information Techno-logy Innovation Project(2023IT056).

摘要: 随着信息技术和制造技术的深度融合,云制造工业生产已成为制造业的关键部分。云制造环境的动态性和服务资源间的相互依赖关系,使得选择最佳工业资源服务变得困难。现有的选择优化方法大多基于启发式算法,但这些算法往往缺乏对云制造环境的自适应能力。因此,文中构建了一种云制造环境下的服务选择模型,提出了一种基于深度学习和生成对抗网络思想的服务选择算法,该模型能够灵活适应环境变化,利用图表示学习方法构建任务服务约束图,根据任务、服务和工业生产约束之间的内在联系学习资源服务特征,在算法改进阶段引入梯度优化和损失函数策略,选择最佳工业资源服务。实验结果表明,所提算法相较于其他对比算法表现出了更强的性能优势。

关键词: 云制造, 工业生产约束, 图表示学习, 生成对抗网络, 梯度损失函数

Abstract: With the deep integration of information technology and manufacturing technology,cloud manufacturing industrial production has become a key part of the manufacturing industry.Due to the dynamics of the cloud manufacturing environment and the interdependencies between service resources,it isn’t easy to select the best industrial resource services.Most of the existing selection optimization methods are based on heuristic algorithms,but these algorithms cannot often adapt to the cloud manufacturing environment.Therefore,this paper constructs a service selection model in the cloud manufacturing environment,proposes a service selection algorithm based on deep learning and generative adversarial network ideas,which can flexibly adapt to environmental changes,uses the graph representation learning method to construct a task service constraint graph,and then learns the characteristics of resource services according to the intrinsic relationship between tasks,services,and industrial production constraints,and introduces gradient optimization and loss function strategies in the algorithm improvement stag and select the best industrial resource services.Experiments show that the proposed algorithm has stronger performance advantages than other comparison algorithms.

Key words: Cloud manufacturing, Industrial production constraints, Graph represents learning, Generate adversarial networks, Gradient loss function

中图分类号: 

  • TP399
[1]TAO F,HU Y F,ZHOU Z D.Study on manufacturing grid &its resource service optimal-selection system[J].The International Journal of Advanced Manufacturing Technology,2008,37:1022-1041.
[2] ZHANG L,LUO Y,TAO F,et al.Cloud manufacturing:a new manufacturing paradigm[J].Enterprise Information Systems,2014,8(2):167-187.
[3]HANNA A C,WHITING J,HUANG B,et al.Heuristic algorithms for design of integrated monitoring of geologic carbon storage sites[J].International Journal of Greenhouse Gas Control,2024,135:104157.
[4] BAHGA T,MOHAMED S M,SEBAQ A M.An Analytical Computational Algorithm for Solving a System of Multipantograph DDEs Using Laplace Variational Iteration Algorithm [J].Advances in Astronomy,2021,1:7741166.
[5] XIAO Y,GU Z,ZHANG Q,et al.New semi-analytical algorithm for solving PKEs based on Euler-Maclaurin approximation [J].Annals of Nuclear Energy,2020,141:107308-107308.
[6]ZHANG H,WU X J,WANG J.Study on the Evaluation Theoretical Structure Building of Deep Learning[J].China Educational Technology,2014,7:51-55.
[7]CHEN E,ANDERSEN S M,CHANDRA R.Deep learningframework with Bayesian data imputation for modelling and forecasting groundwater levels [J].Environmental Modelling and Software,2024,178:106072.
[8]CHU N,NG K K H,LIU Y,et al.Assessment of approach separation with probabilistic aircraft wake vortex recognition via deep learning[J].Transportation Research Part E:Logistics and Transportation Review,2024,181:103387.
[9]LI H,TONG J,ZHANG Z,et al.Selection of resource service chain with conflict-free dependencies in cloud manufacturing systems[J].International Journal of Internet Manufacturing and Services,2020,7(3):216-236.
[10]ZHANG Q,LI S,PU R,et al.An adaptive robust service composition and optimal selection method for cloud manufacturing based on the enhanced multi-objective artificial hummingbird algorithm[J].Expert Systems with Applications,2024,244:122823.
[11]YANG B,WANG S,LI S,et al.A robust service compositionand optimal selection method for cloud manufacturing[J].International Journal of Production Research,2022,60(4):1134-1152.
[12]SUTTON R S,BARTO A G.Reinforcement learning:An introduction[J].Robotica,1999,17(2):229-235.
[13]TESAURO G.TD-Gammon,a self-teaching backgammon program,achieves master-level play[J].Neural computation,1994,6(2):215-219.
[14]DE BLASI S,KLÖSER S,MÜLLER A,et al.KIcker:an industrial drive and control foosball system automated with deep reinforcement learning[J].Journal of Intelligent & Robotic Systems,2021,102(1):20.
[15]LIU Y,YAO J,LIN T,et al.A framework for industrial robot training in cloud manufacturing with deep reinforcement lear-ning[C]//International Manufacturing Science and Engineering Conference.American Society of Mechanical Engineers,2020
[16]MA Y,XU W,TIAN S,et al.Knowledge graph-based manufacturing capability service optimal selection for industrial cloud robotics[C]//International Manufacturing Science and Enginee-ring Conference.American Society of Mechanical Engineers,2020.
[17]DU H,XU W,YAO B,et al.Collaborative optimization of service scheduling for industrial cloud robotics based on knowledge sharing[J].Procedia CIRP,2019,83:132-138.
[18]GUO X,SHI L,CHEN X,et al.TAI-GAN:A Temporally and Anatomically Informed Generative Adversarial Network for early-to-late frame conversion in dynamic cardiac PET inter-frame motion correction[J].Medical Image Analysis,2024:96:103190.
[19] WANG R.Research on communication user churn predictionmodel based on GAN [D].Jiangxi:Jiangxi Normal University,2023.
[20]NIU L,LI Z,LI S.MMD Fence GAN Unsupervised Anomaly Detection Model Based on Maximum Mean Discrepancy[J].International Journal of Cognitive Informatics and Natural Intelligence,2024,18(1):1-13.
[21] CUI F,GENG N,JIANG Z B,et al.Research on Joint Optimization of Reconfigurable Manufacturing Flow Line Configuration and Production Planning under Uncertain Demand[J].Frontier of Engineering Management Technology,2024,43(2):29-37.
[22]SAATY L T.Correction to:Some mathematical concepts of the analytic hierarchy process [J].Behaviormetrika,2021,48(1):1-2.
[23]HUANG J J,CHEN Y C.Resource Allocation of CooperativeAlternatives Using the Analytic Hierarchy Process and Analytic Network Process with Shapley Values [J].Algorithms,2024,17(4):152.
[24]AUGUSTINAS M,ANDREJ B,REGINA O Š,et al.Decision Tree and AHP Methods Application for Projects Assessment:A Case Study [J].Sustainability,2021,13(10):5502-5502.
[25]WU H,CAI X,FENG M.Risk management of engineering projects installation using analytic hierarchy process [J].Infrastructure Asset Management,2024,3:1-39.
[26]ARıCAN H O,KARA E G E.Selection model of chemical tan-ker ships for cargo types using fuzzy AHP and fuzzy TOPSIS [J].Regional Studies in Marine Science,2024,78:103724-103724.
[27] CAO Y,WANG S,KANG L,et al.A TQCS-based service selection and scheduling strategy in cloud manufacturing [J].The International Journal of Advanced Manufacturing Technology,2016,82(1/2/3/4):235-251.
[28]WEI Y,DENG Y,SUN C,et al.Deep learning with noisy labels in medical prediction problems:a scoping review[J].Journal of the American Medical Informatics Association,2024,31(7):1596-1607.
[29]KISHORE A,KUMAR A,DANG N.Enhanced Image Restoration by GANs using Game Theory [J].Procedia Computer Science,2020,173(C):225-233.
[30]XU K,HU W,LESKOVEC J,et al.How powerful are graphneural networks?[J].arXiv:1810.00826,2018.
[31] KUMAR S G,JATOTH C,GANGADHARAN G,et al.QoS-aware cloud service composition using eagle strategy [J].Future Generation Computer Systems,2018,90:273-290.
[32] ZHANG Z,XU X,GAO F,et al.An adaptive approach to manufacturing service portfolio based on dynamic matching network[J].Journal of Software,2018,29:3355-3373.
[33] WANG X,XU H,WANG X,et al.A graph neural network and pointer network-based approach for QoS-aware service composition[J].IEEE Transactions on Services Computing,2022,16(3):1589-1603.
[34]WANG H,LI J,YU Q,et al.Integrating recurrent neural networks and reinforcement learning for dynamic service composition[J].Future Generation Computer Systems,2020,107:551-563.
[35]JIA W,CHEN S,YANG L,et al.Ankylosing spondylitis prediction using fuzzy K-nearest neighbor classifier assisted by modified JAYA optimizer[J].Computers in Biology and Medicine,2024,175:108440.
[36]MONGE J J,PARKER W J,RICHARDSON J W.Integratingforest ecosystem services into the farming landscape:a stochastic economic assessment[J].Journal of Environmental Management,2016,174:87-99.
[37] FREIBOTT C R,GERBOLÉS C G C,SÁNCHEZ G A,et al.MILP and PSO approaches for solving a hydropower reservoirs intraday economic optimization problem[J/OL].https://link.springer.com/article/10.1007/s10100-024-00934-z.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!