Real-time scheduling for production-logistics collaborative environment using multi-agent deep reinforcement learning

Advanced Engineering Informatics, Journal Year: 2025, Volume and Issue: 65, P. 103216 - 103216

Published: Feb. 23, 2025

Language: Английский

---

Dynamic Event‐Triggered Consensus for Switched Nonlinear Systems in Intelligent Manufacturing

IET Collaborative Intelligent Manufacturing, Journal Year: 2025, Volume and Issue: 7(1)

Published: Jan. 1, 2025

ABSTRACT Multiagent cooperative control enhances system efficiency through the facilitation of distributed collaboration, demonstrating significant applications in intelligent manufacturing. As a fundamental issue control, multiagent consensus has been implemented extensively numerous domains. Therefore, this paper studies asymptotic nonlinear under switching topologies. The changeable topological structures hinder system's ability to stabilise or require substantial amount time for stabilisation. To address issue, we have incorporated information into traditional Riccati equation. Subsequently, topology‐based dynamic event‐triggered mechanism is presented by introducing an internal variable based on solution Furthermore, research proposes novel protocol that utilises full This contains gain, which allows adjustment law response communication topology. Then, Lyapunov stability theory guarantees reaches proposed law. study also proves does not exhibit Zeno behaviour. Ultimately, simulation results confirm viability protocol.

Language: Английский

---

Enhancing Construction Management Digital Twins Through Process Mining of Progress Logs

Sustainability, Journal Year: 2024, Volume and Issue: 16(22), P. 10064 - 10064

Published: Nov. 19, 2024

Large-scale infrastructure projects involve numerous complex processes, and even small construction management (CM) deficiencies can lead to significant resource waste. Digital twins (DTs) offer a potential solution the side of problem. The current DT models focus on real-time physical space mapping, which causes fragmentation process data in servers limits lifecycle algorithm implementation. In this paper, we propose framework that integrates achieve discovery through mining serves as supplement DTs. proposed was validated highway project. Based BIM, GIS, UAV entity twins, logs were collected, performed them using techniques, achieving mapping conformance checking for twins. main conclusions are follows: (1) accurately reflect actual process, addressing lack information CM DTs; (2) variants be used analyze abnormal changes methods identify risks advance; (3) sudden nodes during activities affect allocation across multiple subsequent stages; (4) visualize schedule risks, such lag times. significance paper lies complement existing framework, providing lost relationships DTs, enabling better reproduction, facilitating prediction optimization. future work, will concentrate conducting more in-depth research drawing from wider range sources advancing intelligent techniques.

Language: Английский

---

Efficient Task Scheduling Using Constraints Programming for Enhanced Planning and Reliability

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(23), P. 11396 - 11396

Published: Dec. 6, 2024

This paper presents an efficient schedule method for maintenance, repair, and overhaul (MRO) tasks aircraft engines using a constraint programming algorithm. Using data obtained from Korean Air’s MRO maintenance logs, we analyze predict the optimal scheduling of regular inspections fault repairs various engine types. By proposing proper modeling problem preparing algorithm, demonstrate superior performance in efficiency resource utilization. The experimental results show average utilization 99.35%, can even achieve 100% some cases.

Language: Английский

---