Wednesday, October 16th 2024

(Milan Time) 15:00-17:30

(Beijing Time) 21:00-23:30

Tencent ID : 734-244-443

Weblink: https://meeting.tencent.com/dm/hTDnINQfyN1W

Session Aims & Scope

In order to make the logistics system more efficient and cost-effective, the requirements for intelligent upgrading of the logistics system are becoming higher and higher. More and more machines and robots are being put into logistics links such as warehousing, sorting, packaging, and transportation. Humans, machines, and robots together constitute an intelligent logistics system. The intelligent logistics system pays more attention to the group performance composed of machines, humans, and robots, rather than individual performance. Therefore, accurately predicting system performance is a prerequisite for making optimal design and control. Traditional methods are lacking in this respect, and digital twins bring new ideas to solve this problem. As an emerging technology, digital twins build connections between physical systems and virtual systems to make the virtual system more realistic and can be applied to the design, debugging, and operation and maintenance of logistics systems. In recent years, research and applications of logistics system digital twins (LDT) have emerged in an endless stream, gradually becoming a research point worldwide. This session is arranged for recent theoretical and application perspectives, presenting innovative academic and practical researches.

 

The session will focus on the following points.

Methodologies of combing logistics system and digital twin.

AI for LDT.

Innovative researches of RDT

Advanced application researches of LDT

Performance prediction of logistics system via LDT

Session Chair(s)

Chair

Ning Zhao

Professor

University of Science and Technology Beijing (China)

Co-Chair

Ting Qu

Professor

Jinan University (China)

Co-Chair

Wenfeng Li

Professor

Wuhan University Of Technology (China)

Co-Chair

Haobin Li

Senior Lecturer

National University of Singapore (Singapore)

Co-Chair

Jianbin Xin

Associate Professor

Zhengzhou University (China)

Session Presentation

1.

Mahnam Saeednia

Assistant Professor

Delft University of Technology (The Netherlands)

Title: Rethinking Freight: Unlocking the Potential of Digital Twins for a Greener Transport

Abstract 

As freight transport industry is under pressure to reduce emissions towards net-zero, digitalization becomes not just a powerful tool, but an essential enabler. The digital transformation is gaining momentum and is increasingly critical in the face of climate change and extreme events. Although Digital Twins have yet to see widespread adoption in the logistic sector, many foundational technologies are already in place. These include advanced tracking and tracing systems, open API strategies, and the shift to cloud-based IT infrastructures. Additionally, progress in machine learning and advanced analytics is enabling optimization of supply chains and providing new insights from historical shipment and operational data. Logistic professionals are also leveraging augmented, mixed, and virtual reality applications for tasks like warehouse picking and vehicle loading. The data generated from these activities is particularly well-suited for the creation of Digital Twins in these environments. As a result, the industry is presented with unique opportunities to accelerate the use of Digital Twins across the sector. The ongoing exploration of potential use cases for Digital Twins in logistics is crucial for preparing the sector for full-scale implementation in the coming years. As other industries begin to embrace this technology, it is essential for the logistics sector to position itself within a broader context of digital transformation and innovation.

2.

Mengya LIU

Research Fellow

National University of Singapore (Singapore)

Title: Enhancing Container Terminal Operations Through a Four-Dimensional Digital Twin Framework

Abstract 

Digital Twins have advanced into a key technology for enabling real-time decision-making and optimizing operations, especially in the highly complex context of mega container terminals. A Digital Twin framework of four dimensions — Connectivity, Visibility, Fidelity, and Analyzability —can be implemented and tailored to meet the unique demands of these terminals: Seamless data integration, intuitive visualization of terminal processes, precise modelling, and advanced analytical capabilities provide operators with critical insights into container movements, resource allocation, and bottleneck identification. This framework not only improves operational efficiency but also enhances the ability to predict and optimize performance in a dynamic logistics landscape. The progressive development of this system offers a roadmap for advancing global logistics through smarter and more responsive terminal operations.

3.

Ning ZHAO

Assistant Professor , FHEA, CEng, IMechE, PhD

University of Birmingham (UK)

Title: The implementation of Train Intelligent Driving Strategy with Digital Twin

Abstract 

Rail systems consume a considerable amount of energy in day-to-day operations. Due to increasing environmental concerns, rail operators are under growing pressure to conserve energy. An effective strategy for controlling driving can significantly impact energy-saving performance. At BCRRE, we collaborated with Ricardo to develop an intelligent driving strategy solution, initially sponsored by UK Tram. This technology aims to provide enhanced control strategies for drivers to achieve energy-efficient operation. By implementing digital twin technology, our team modelled the route and identified the optimal driving strategy for individual route sections. “We aim to improve drivers, rather than replace them with machines.” This solution has been successfully implemented by Edinburgh Trams since 2019, resulting in significant energy savings. Edinburgh Trams was even awarded a Highly Commended recognition in the Best Environmental and Sustainability Initiative category at the Global Light Rail Awards.

4.

Lei CAI

PhD student

Wuhan University of Technology (China)

Title: Digital twin-driven proactive-reactive scheduling framework for port multi-equipment under a complex uncertain environment

Abstract 

The pervasive uncertainties in multiple port equipment scheduling frequently result in container handling delays or ineffective plans. To address the complexities and uncertainties of port multiple equipment integrated scheduling problem, this presentation introduces a Digital Twin-driven (DT- driven) proactive-reactive scheduling framework. This framework is designed to promptly respond to uncertainties in the scheduling process and provide a transparent visualization of operational information. By developing a virtual container port simulation, which features a U-shaped port layout and double-cycling mode drawn from real-world scenarios, the presentation evaluates the proposed framework’s effectiveness. The experimental results demonstrate that the DT-driven framework significantly improves efficiency and conserves energy. Additionally, in large-scale conditions, the makespan difference between the DT-driven approach and the non-DT-driven approach is as much as 19.56 %. In terms of energy consumption savings, the DT-driven approach’s scheduling plan can save 3.67 % of energy consumption under large-scale conditions. Moreover, as the disturbance degree increases, the energy consumption savings become even more significant.

5.

Lin MA

Postdoctoral Research Fellow

Jinan University Zhuhai Campus (JNU) (China)

Title: A Bottleneck Dynamic Detection and Workload Control Method for Synchronized Production System Based on Digital Twin Workload Space

Abstract 

The client demands exhibit high uncertainty in Industry 4.0, which poses challenges for the Production Planning and Control (PPC) in Multi-Cellular Synchronized Production System (MCSPS). Conventional reactive PPC solutions often result in imbalanced workloads across the units due to insufficient overall capacity. In response, we shift our insights from “real-time capacity assessment for deterministic demands” to “timely workload space reservation for uncertain demands”, and introduce a digital twin-based workload space to balance the real-time operational states, including actual workload, adaptive equilibrium, and ideal equilibrium. This research emphasizes throughput bottleneck detection through real-state mapping, optimization of workload balancing via global decision-making, and probability-based methods to achieve balance in the ideal state. Additionally, the control structure evolves from single-level to cascade control. The outcomes will be tested using a laboratory physical factory model.

6.

Yangjun SUN

Post-Doctoral Researcher

University of Science and Technology Beijing (China)

Title: Centralized scheduling approach based on digital twin for robotic scheduling in robotic mobile fulfillment systems

Abstract 

The Robotic Mobile Fulfillment System (RMFS) is a “goods-to-worker” system that utilizes pods to store goods and employs robots for pods movement. Due to the common problems of “many conflicts, chain conflicts, and frequent deadlock” in a large number of mobile robots operation, the system is inefficient, and even regional downtime. To solve this problem, a centralized scheduling approach based on digital twin for robotic scheduling was proposed. A digital twin model with physical system, virtual system, twin data center, and support services for system operation was established. Instruction acceptance and data acquisition mechanism for physical system, scheme generation and simulation mechanism for virtual system, and data processing and comparison mechanism for twin data center are established. Support services for system operation is used to ensure the smooth operation of the three mechanisms. Conflict prediction is achieved through a digital twin system to obtain an optimized conflict-free scheduling scheme when the robot is not yet operational. Through the data interaction between physical system and virtual system, real-time scheduling is ensured when orders continue to arrive. According to different disturbances in RMFS, the rescheduling rules are determined to generate new schemes. Through cases, the research and application scenarios of the above methods in the future are illustrated.