Learning to schedule dynamic distributed reconfigurable workshops using expected deep Q-network

Advanced Engineering Informatics, Год журнала: 2023, Номер 59, С. 102307 - 102307

Опубликована: Дек. 15, 2023

Язык: Английский

---

A deep reinforcement learning method based on a multiexpert graph neural network for flexible job shop scheduling

Computers & Industrial Engineering, Год журнала: 2024, Номер unknown, С. 110768 - 110768

Опубликована: Дек. 1, 2024

Язык: Английский

---

Study on the Multi-Equipment Integrated Scheduling Problem of a U-Shaped Automated Container Terminal Based on Graph Neural Network and Deep Reinforcement Learning

Journal of Marine Science and Engineering, Год журнала: 2025, Номер 13(2), С. 197 - 197

Опубликована: Янв. 22, 2025

Intelligent Guided Vehicles (IGVs) in U-shaped automated container terminals (ACTs) have longer travel paths than those conventional vertical layout ACTs, and their interactions with double trolley quay cranes (DTQCs) cantilever rail (DCRCs) are more frequent complex, so the scheduling strategy of a traditional ACT cannot easily be applied to ACT. With aim minimizing maximum task completion times within ACT, this study investigates integrated problem DTQCs, IGVs DCRCs under hybrid “loading unloading” mode, expresses as Markovian decision-making process, establishes disjunctive graph model. A deep reinforcement learning algorithm based on neural network combined proximal policy optimization is proposed. To verify superiority proposed models algorithms, instances different scales were stochastically generated compare method several heuristic algorithms. This also analyses idle time equipment two loading unloading modes, results show that mode can enhance operational effectiveness.

Язык: Английский

---

Deep reinforcement learning-based memetic algorithm for solving dynamic distributed green flexible job shop scheduling problem with finite transportation resources

Swarm and Evolutionary Computation, Год журнала: 2025, Номер 94, С. 101885 - 101885

Опубликована: Фев. 21, 2025

Язык: Английский

---

TDCR: Transformer based decision conflict resolution model for collaborative scheduling

Neurocomputing, Год журнала: 2025, Номер unknown, С. 129760 - 129760

Опубликована: Фев. 1, 2025

Язык: Английский

---

Harnessing heterogeneous graph neural networks for Dynamic Job-Shop Scheduling Problem solutions

Computers & Industrial Engineering, Год журнала: 2025, Номер unknown, С. 111060 - 111060

Опубликована: Март 1, 2025

Язык: Английский

---

Solving quay wall allocation problems based on deep reinforcement learning

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 150, С. 110598 - 110598

Опубликована: Апрель 4, 2025

Язык: Английский

---

Deep reinforcement learning for solving efficient and energy-saving flexible job shop scheduling problem with multi-AGV

Computers & Operations Research, Год журнала: 2025, Номер unknown, С. 107087 - 107087

Опубликована: Апрель 1, 2025

Язык: Английский

---

A deep reinforcement learning approach with graph attention network and multi-signal differential reward for dynamic hybrid flow shop scheduling problem

Journal of Manufacturing Systems, Год журнала: 2025, Номер 80, С. 643 - 661

Опубликована: Апрель 14, 2025

Язык: Английский

---

Dynamic job shop scheduling under multiple order disturbances using deep reinforcement learning

Science Progress, Год журнала: 2025, Номер 108(2)

Опубликована: Апрель 1, 2025

Dynamic job shop scheduling problems with multiple order disturbances present significant challenges in manufacturing systems. This paper proposes a novel approach using Independent Proximal Policy Optimization (IPPO), multiagent deep reinforcement learning algorithm, to address these challenges. We introduce five-channel two-dimensional image represent system states and design reward function that minimizes both total tardiness makespan. Experimental results across 72 diverse production scenarios demonstrate our IPPO-based outperforms traditional algorithms dispatching rules most cases. The proposed method shows strong optimization exploration capabilities, offering promising solution for complex, multiobjective dynamic environments.

Язык: Английский

---