A Topology-Aware Optimization Framework for Conveyor System Scheduling

DOI: https://doi.org/10.62517/jes.202502303

Author(s)

Guodong Wang

Affiliation(s)

School of Computer Science and Technology, Qingdao University, Qingdao, Shandong, China

Abstract

In modern industrial settings, conveyor systems often involve multiple devices working together, changing tasks, and complex scheduling needs. A common challenge is the lack of effective modeling of how devices are connected and how their working states depend on each other. Traditional scheduling methods usually make decisions based only on local information or the state of a single device, which makes it hard to respond quickly and efficiently at the system level. To address this, we propose a dynamic scheduling method for conveyor systems based on graph neural networks (GNNs). First, industrial cameras capture real-time image sequences to estimate the speed of each conveyor belt and extract visual features. These are used to build small time-based graphs, which are then combined into a full system graph. The GNN learns the relationships and dependencies between devices to create a global state representation. Using this representation, a reinforcement learning-based policy network is trained to automatically adjust the belt speeds. A visual feedback loop is also introduced to enable continuous online learning. Additionally, we design a method to dynamically split and compress the system graph to improve modeling efficiency and scheduling accuracy. Experiments show that this method offers better flexibility, stability, and energy efficiency under complex conveyor conditions.

Keywords

Conveyor System Scheduling; Topology-Aware Optimization; Graph Neural Networks; Reinforcement Learning

References

[1] K. Wang, Q. Hu, M. Zhou, Z. Zun, and X. Qian, “Multi-aspect applications and development challenges of digital twin-driven management in global smart ports,” Case Studies on Transport Policy, vol. 9, no. 3, pp. 1298–1312, 2021. [2] C. Zhang, H. Hu, Y. Yang, and N. Wang, “Optimizing the portfolio of smart technologies to maximize port carbon emission efficiency: a configurational theory approach,” Maritime Policy & Management, pp. 1–39, 2025. [3] L. Tang and Y. Meng, “Data analytics and optimization for smart industry,” Frontiers of Engineering Management, vol. 8, no. 2, pp. 157–171, 2021. [4] W. Mi and Y. Liu, “Development trend and target of smart port,” in Smart Ports. Springer, 2022, pp. 189–201. [5] X. Wang and H. Shi, “Research on intelligent optimization of bulk cargo terminal control system,” in Journal of Physics: Conference Series, vol. 1601, no. 5. IOP Publishing, 2020, pp. 052044. [6] C. F. Fontana, F. Papa, C. L. Marte, L. R. Yoshioka, and C. A. Sakurai, “Intelligent transportation system as a part of seaport terminal management system,” International journal of systems applications, engineering & development, vol. 8, pp. 41–46, 2014. [7] W. Wang, A. Ding, Z. Cao, Y. Peng, H. Liu, and X. Xu, “Deep reinforcement learning for channel traffic scheduling in dry bulk export terminals,” IEEE Transactions on Intelligent Transportation Systems, 2024. [8] X. Song and L. Huang, “Optimization of import business process and system design in bulk port based on internet of things.” in ICEIS (4), 2011, pp. 509–512. [9] S. Liu, Q. Liu, L. Wang, and X. Chen, “Intelligent bulk cargo terminal scheduling based on a novel chaotic-optimal thermodynamic evolutionary algorithm,” Complex & Intelligent Systems, vol. 10, no. 6, pp. 7435–7450, 2024. [10] H. Shi, X. Wang, H. Zhou, and N. Lu, “Research on monitoring and diagnosis model of dry bulk terminal conveying equipment based on edge-cloud collaborative technology,” in 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), vol. 12350. SPIE, 2022, pp. 359–364. [11] S. Liu, W. Wang, S. Zhong, Y. Peng, Q. Tian, R. Li, X. Sun, and Y. Yang, “A graph-based approach for integrating massive data in container terminals with application to scheduling problem,” International Journal of Production Research, vol. 62, no. 16, pp. 5945–5965, 2024. [12] W. Yang, X. Bao, Y. Zheng, L. Zhang, Z. Zhang, Z. Zhang, and L. Li, “A digital twin framework for large comprehensive ports and a case study of qingdao port,” The International Journal of Advanced Manufacturing Technology, vol. 131, no. 11, pp. 5571–5588, 2024. [13] B. Greve, N. M. Ahmed, M. Knauer, C. Wanigasekara, and F. S. Torres, “Optimal control of maritime container terminal operations for effective utilization of resources,” IEEE Transactions on Intelligent Transportation Systems, 2025. [14] Y. Li, L. Chen, M. Chen, and X. Qian, “Integrating spatial cognition and slam for improved performance of autonomous material handling robots in dynamic stockyard environments,” Industrial Robot: the international journal of robotics research and application, 2025. [15] J. Xin, R. R. Negenborn, and G. Lodewijks, “Energy-aware control for automated container terminals using integrated flow shop scheduling and optimal control,” Transportation Research Part C: Emerging Technologies, vol. 44, pp. 214–230, 2014. [16] F. Zeng, Q. Wu, and C. Dai, “Speed control simulation system of bulk terminal conveyor belts,” in ICTIS 2013: Improving Multimodal Transportation Systems- Information, Safety, and Integration, 2013, pp. 2062–2069. [17] Y. Lv, Y. Gao, and J. Liu, “Dual strategies-based resilience enhancement in a bulk cargo port under dynamic machinery failure scenarios with reinforcement learning,” Ocean & Coastal Management, vol. 260, pp. 107484, 2025. [18] H. Shi and X. Wang, “Study on optimization of monitoring system of belt conveyor in dry bulk wharf,” in 2nd International Conference on Laser, Optics and Optoelectronic Technology (LOPET 2022), vol. 12343. SPIE, 2022, pp. 597–601. [19]M. Tang, D. Gong, S. Liu, and H. Zhang, “Applying multi-phase particle swarm optimization to solve bulk cargo port scheduling problem,” Advances in Production Engineering & Management, vol. 11, no. 4, p. 299, 2016. [20] A. Ridwan, “Container ship planning optimization using intelligent meta-heuristic algorithms,” Industrial Engineering & Management Systems, vol. 21, no. 3, pp. 460– 468, 2022. [21] L. Henesey, “Multi-agent systems for container terminal management,” Ph.D. dissertation, Blekinge Institute of Technology, 2006. [22] R.-A. Daineanu, N.-M. Zus, M. Panaitescu, F.-V. Panaitescu, and D. Dinu, “The dynamics of a maritime container terminal complex system: optimization process design,” in Advanced Topics in Optoelectronics, Microelectronics, and Nanotechnologies XI, vol. 12493. SPIE, 2023, pp. 51–60. [23] M. Jusis, “Method of data synchronization of autonomous port handling processes,” Ph.D. dissertation, Vilniaus universitetas, 2021. [24] H. Yin, Z. Wang, and N. K. Jha, “A hierarchical inference model for internet-of-things,” IEEE Transactions on Multi-Scale Computing Systems, vol. 4, no. 3, pp. 260–271, 2018.