Article
Computer Science, Interdisciplinary Applications
Zhuo Zhou, Liyun Xu, Xufeng Ling, Beikun Zhang
Summary: Job scheduling is crucial for production management, and a digital-twin-based strategy is proposed to overcome the limitations of traditional scheduling methods. This strategy includes the introduction of energy consumption, establishment of a scheduling model, proposal of a cloud-edge computing decision framework, and design of a DT-based shop scheduling strategy. The non-dominated sorting genetic algorithm is also improved to enhance the scheduling performance. Experimental results demonstrate the effectiveness of the proposed strategy and algorithm.
INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING
(2023)
Article
Computer Science, Interdisciplinary Applications
Jin Wang, Yang Liu, Shan Ren, Chuang Wang, Shuaiyin Ma
Summary: This paper proposes a real-time digital twin flexible job shop scheduling method with edge computing to address the issue of abnormal disturbances in production. It presents an overall framework for real-time scheduling and utilizes an improved Hungarian algorithm to obtain the optimal result. The method effectively deals with unexpected disruptions in the production process.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2023)
Article
Engineering, Industrial
Meng Zhang, Fei Tao, A. Y. C. Nee
Summary: This paper discusses how digital twin technology can be used for machine availability prediction, disturbance detection, and performance evaluation in dynamic scheduling of job-shop operations. A methodology for DT-enhanced dynamic scheduling is proposed, and a case study on producing hydraulic valves in a machining job-shop demonstrates the effectiveness and advantages of the approach.
JOURNAL OF MANUFACTURING SYSTEMS
(2021)
Article
Computer Science, Interdisciplinary Applications
Yibing Li, Zhiyu Tao, Lei Wang, Baigang Du, Jun Guo, Shibao Pang
Summary: This paper proposes a framework for anomaly detection and dynamic scheduling in flexible job shop based on digital twin technology. It enables real-time monitoring and optimization of scheduling, reduces deviation, and has been successfully applied in equipment manufacturing job shop.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2023)
Article
Computer Science, Interdisciplinary Applications
Jun Yan, Zhifeng Liu, Caixia Zhang, Tao Zhang, Yueze Zhang, Congbin Yang
Summary: This study addresses the impact of finite transportation conditions on scheduling in the flexible job shop scheduling problem and proposes a method to improve the scheduling results. The results show that finite transportation conditions significantly affect scheduling under different scales of scheduling problems and transportation times.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2021)
Article
Management
Karim Tamssaouet, Stephane Dauzere-Peres
Summary: This article presents a framework that unifies and generalizes well-known literature results on local search for job-shop and flexible job-shop scheduling problems. The proposed framework focuses on quickly ruling out infeasible moves and evaluating the quality of feasible neighbors, which are crucial for the success of local search approaches. It can be applied to any scheduling problem with an appropriate defined neighborhood structure. The proposed framework introduces novel procedures for evaluating feasibility and estimating the value of objective functions for neighbor solutions.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2023)
Article
Mathematics, Interdisciplinary Applications
Juan Li, Xianghong Tian, Jing Liu
Summary: In this paper, a flexible industrial job shop dynamic data scheduling method based on digital twin technology is proposed. By building an all-factor digital information fusion model and introducing a CGA algorithm based on cloud model, the dynamic data scheduling of the flexible industrial job shop is achieved. Experimental results show that the method can complete the coordinated scheduling among multiple production lines in the least amount of time.
DISCRETE DYNAMICS IN NATURE AND SOCIETY
(2022)
Article
Engineering, Industrial
L. Huo, J. Y. Wang
Summary: This study proposes a hybrid dynamic scheduling method with Digital Twin and improved bacterial foraging algorithm (IBFOA) to optimize the complex workpiece processing in a job shop. The results show that this method can effectively minimize the maximum completion time and machine load, and address the issue of extended production time caused by disruptions.
INTERNATIONAL JOURNAL OF SIMULATION MODELLING
(2022)
Article
Computer Science, Artificial Intelligence
Khalil Tliba, Thierno M. L. Diallo, Olivia Penas, Romdhane Ben Khalifa, Noureddine Ben Yahia, Jean-Yves Choley
Summary: This research proposes a digital twin-driven dynamic scheduling approach for a real hybrid flow shop in a perfume manufacturing company, combining optimization and simulation to address the specific constraints of the case study.
JOURNAL OF INTELLIGENT MANUFACTURING
(2023)
Article
Automation & Control Systems
Qiyue Wang, Wenhua Jiao, Peng Wang, YuMing Zhang
Summary: This paper introduces an innovative investigation on prototyping a digital twin as a platform for human-robot interactive welding and welder behavior analysis. The study shows that the human-robot interaction working style and data-driven welder behavior analysis can enhance operational productivity and accelerate novice welder training.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2021)
Article
Automation & Control Systems
Zhenyu Zhou, Zehan Jia, Haijun Liao, Wenbing Lu, Shahid Mumtaz, Mohsen Guizani, Muhammad Tariq
Summary: Digital twin (DT) provides accurate guidance for multidimensional resource scheduling in 5G edge computing-empowered distribution grids by establishing a digital representation of physical entities. This article addresses the critical challenges of DT construction and DT-assisted resource scheduling, proposing a federated learning-based DT framework and a Secure and lAtency-aware dIgital twin assisted resource scheduliNg algoriThm (SAINT) to achieve low-latency, accurate, and secure DT. SAINT supports intelligent resource scheduling by improving the learning performance of deep Q-learning and considers access priority and energy consumption awareness.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Interdisciplinary Applications
Yongli Wei, Tianliang Hu, Yanqing Wang, Shiyun Wei, Weichao Luo
Summary: The paper investigates the implementation strategy of physical entity for manufacturing system Digital Twin (DT), focusing on application-oriented requirements analysis and optimal requirements deployment scheme with Axiomatic Design (AD) theory. Through a case study on Computer Numerical Control Machine Tools (CNCMT) cutting tool life prediction, the proposed strategy's implementation flow, operability, and effectiveness are demonstrated.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2022)
Article
Computer Science, Information Systems
Yiwen Wu, Ke Zhang, Yan Zhang
Summary: Digital twin network (DTN) utilizes digital twin (DT) technology to create virtual twins of physical objects, enabling co-evolution between physical and virtual spaces. Key applications include manufacturing, aviation, healthcare, and intelligent transportation systems, with current technical challenges and future trends identified.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Interdisciplinary Applications
Zhi Li, Yingjian Chen
Summary: This paper introduces digital twin as a newly-emerged enabling technology for intelligent manufacturing and discusses its challenges and requirements. It also proposes a digital twin-driven dynamic scheduling strategy to address the flexible job shop scheduling problem.
COMPUTERS & INDUSTRIAL ENGINEERING
(2023)
Article
Engineering, Manufacturing
Zhaoming Chen, Jinsong Zou, Wei Wang
Summary: This paper proposes a multi-objective flexible job shop scheduling model based on digital twin and designs a hybrid particle swarm optimization method to solve the problem. The obtained Pareto optimal solution set is analyzed to obtain a satisfactory solution. A three-dimensional model is built using Plant Simulation software, and the scheduling process is simulated and optimized by combining with the production data of an enterprise to verify the feasibility and applicability of the method.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE
(2023)
Article
Computer Science, Information Systems
Zude Zhou, Jianmin Hu, Quan Liu, Ping Lou, Junwei Yan, Wenfeng Li
Article
Mathematics, Interdisciplinary Applications
Ping Lou, Yuting Chen, Song Gao
Article
Computer Science, Artificial Intelligence
Jian Fu, Xiang Teng, Ce Cao, Zhaojie Ju, Ping Lou
Summary: The research proposes a framework based on improved locally weighted regression and policy improvement with path integral for robot intelligent trajectory planning, aiming to address the challenge of generating new robot motions automatically to perform new tasks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Chemistry, Analytical
Ping Lou, Qi Zhao, Xiaomei Zhang, Da Li, Jiwei Hu
Summary: This paper proposes an indoor positioning system using UWB technology and digital twin, which improves the positioning accuracy through perception-prediction feedback. In addition, an anchor layout method with virtuality-reality interaction and an error mitigation method based on neural networks are introduced in this system.
Article
Mathematics
Ping Lou, Yutong Zhong, Jiwei Hu, Chuannian Fan, Xiao Chen
Summary: This paper proposes a digital-twin-driven AGV scheduling and routing framework to address uncertainties in automated container terminals (ACT). By introducing a digital twin, uncertain factors can be detected and handled through the interaction and fusion of physical and virtual spaces. The improved artificial fish swarm algorithm Dijkstra (IAFSA-Dijkstra) is proposed for optimal AGV scheduling and routing, which is verified in a virtual space and fed back to the real world for actual AGV transport guidance. Additionally, a twin-data-driven conflict prediction method and conflict resolution method based on the Yen algorithm are explored. The proposed method effectively improves efficiency and reduces the cost of AGV scheduling and routing in ACT, as demonstrated by case study examples.
Article
Mathematics
Ping Lou, Zihao Wu, Jiwei Hu, Quan Liu, Qin Wei
Summary: Traffic flow prediction is important for intelligent transportation systems, as it can help alleviate congestion and improve road traffic safety. However, predicting traffic flow accurately is challenging due to its non-linear and complex patterns influenced by external factors. Most existing short-term traffic flow prediction methods perform poorly for longer time steps.
JOURNAL OF MATHEMATICS
(2023)
Article
Chemistry, Analytical
Ping Han, Xujun Zhuang, Huahong Zuo, Ping Lou, Xiao Chen
Summary: Smart security based on object detection is an important application of edge computing in IoT. The proposed Lightweight Anchor Dynamic Assignment algorithm (LADA) addresses the issues of poor adaptability and difficulty in sample selection by considering the aspect ratio of ground-truth boxes and dynamically dividing positive and negative samples efficiently. Experimental results show that the LADA algorithm outperforms existing sample assignment algorithms in terms of average precision (AP).
Article
Mathematics
Xiaomei Zhang, Fan Yang, Qiwen Jin, Ping Lou, Jiwei Hu
Summary: This paper introduces a reinforcement learning algorithm for dual-arm robot path planning, which improves efficiency through the use of experience replay, shortest-path constraint, and policy gradient. The algorithm demonstrates strong performance in collaborative task execution and addresses the challenge of reward sparsity, as validated through simulations and experiments.
Article
Mathematics
Jiwei Hu, Feng Xiao, Qiwen Jin, Guangpeng Zhao, Ping Lou
Summary: In this paper, a synthetic data generation framework based on image-to-image translation is proposed for industrial object detection tasks. The RDB-CycleGAN network is used to transform CAD models into realistic images. By introducing the SSIM loss function to strengthen network constraints, the generated synthetic data effectively enhances the performance of object detection algorithms on real images.
Article
Engineering, Manufacturing
Lili Zhao, Yilin Fang, Ping Lou, Junwei Yan, Angran Xiao
Summary: This paper presents a cutting parameter optimization method based on digital twins, by establishing an ontology of CNC machining processes to understand real-time interactions between physical machines and virtual twins, improving machining efficiency and reducing carbon emissions.
INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING
(2021)
Article
Computer Science, Information Systems
Ping Lou, Jiwei Hu, Cui Zhu, Junwei Yan, Liping Yuan
Summary: The emergence of service-oriented Cloud Manufacturing (CMfg) relies on technologies like cloud computing and Industrial Internet of Things to distribute and authorize various manufacturing resources. In CMfg, cooperation between multiple Manufacturing Services (MSs) is essential to complete Manufacturing Tasks (MTs) as individual and collective interests may conflict. By exploring individual decision-making behaviors and employing evolutionary game theory and agent-based modeling, efficient methods for maximizing interests through MSs' cooperation can be developed.
Article
Computer Science, Information Systems
Ping Lou, Yuting Chen, Junwei Yan
Article
Computer Science, Information Systems
Ping Lou, Shiyu Liu, Jianmin Hu, Ruiya Li, Zheng Xiao, Junwei Yan
