A Q-learning driven multi-objective evolutionary algorithm for worker fatigue dual-resource-constrained distributed hybrid flow shop

Computers & Operations Research, Год журнала: 2024, Номер unknown, С. 106919 - 106919

Опубликована: Ноя. 1, 2024

Язык: Английский

---

Multi-agent deep reinforcement learning-based approach for dynamic flexible assembly job shop scheduling with uncertain processing and transport times

Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 126441 - 126441

Опубликована: Янв. 1, 2025

Язык: Английский

---

Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions

Computers & Industrial Engineering, Год журнала: 2025, Номер unknown, С. 110856 - 110856

Опубликована: Янв. 1, 2025

Язык: Английский

---

A cooperative hierarchical deep reinforcement learning based multi-agent method for distributed job shop scheduling problem with random job arrivals

Computers & Industrial Engineering, Год журнала: 2023, Номер 185, С. 109650 - 109650

Опубликована: Окт. 4, 2023

Язык: Английский

---

Critical analysis of the impact of artificial intelligence integration with cutting-edge technologies for production systems

Journal of Intelligent Manufacturing, Год журнала: 2023, Номер unknown

Опубликована: Ноя. 13, 2023

Abstract Scientific research on emerging technologies underscored the advantages of their implementation within production systems, with a particular focus artificial intelligence (AI). In particular, integration AI other cutting-edge is relevant topic which can potentially lead to huge impacts in terms business performance. Yet, literature subject, although rich, still fragmented, limited specific cases and applications, but lacking comprehensive classification framework. Therefore, using systematic review, this study provides an overview how combination could improve market organisational performance functions processes. By classifying case studies real-world applications into taxonomies, considers indicator, co-occurrence ratio, highlighting most significant combinations between technologies, also specifying contexts they are used. The shows that strongly interconnected suggesting agenda promising systems contexts, providing benefits opportunities for companies.

Язык: Английский

---

An efficient and adaptive design of reinforcement learning environment to solve job shop scheduling problem with soft actor-critic algorithm

International Journal of Production Research, Год журнала: 2024, Номер unknown, С. 1 - 16

Опубликована: Март 30, 2024

Shop scheduling is deeply involved in manufacturing. In order to improve the efficiency of and fit dynamic scenarios, many Deep Reinforcement Learning (DRL) methods are studied solve problems like job shop flow shop. But most studies focus on using latest algorithms while ignoring that environment plays an important role agent learning. this paper, we design effective, robust size-agnostic for scheduling. The proposed uses centralised training decentralised execution (CTDE) implement a multi-agent architecture. Together with observation space design, environmental information irrelevant current decision eliminated as much possible. action enlarges agents, which performs better than traditional way. Finally, Soft Actor-Critic (SAC) algorithm adapted learning within environment. By comparing rules, other reinforcement algorithms, relevant literature, superiority results obtained study demonstrated.

Язык: Английский

---

Deep reinforcement learning for dynamic distributed job shop scheduling problem with transfers

Expert Systems with Applications, Год журнала: 2024, Номер 251, С. 123970 - 123970

Опубликована: Апрель 17, 2024

Язык: Английский

---

Multi-Agent Reinforcement Learning for Job Shop Scheduling in Dynamic Environments

Sustainability, Год журнала: 2024, Номер 16(8), С. 3234 - 3234

Опубликована: Апрель 12, 2024

In response to the challenges of dynamic adaptability, real-time interactivity, and optimization posed by application existing deep reinforcement learning algorithms in solving complex scheduling problems, this study proposes a novel approach using graph neural networks complete task job shop scheduling. A distributed multi-agent architecture (DMASA) is constructed maximize global rewards, modeling intelligent manufacturing problem as sequential decision represented graphs Graph Embedding–Heterogeneous Neural Network (GE-HetGNN) encode state nodes map them optimal strategy, including machine matching process selection strategies. Finally, an actor–critic architecture-based proximal policy algorithm employed train network optimize decision-making process. Experimental results demonstrate that proposed framework exhibits generalizability, outperforms commonly used rules RL-based methods on benchmarks, shows better stability than single-agent architectures, breaks through instance-size constraint, making it suitable for large-scale problems. We verified feasibility our method specific experimental environment. The research can achieve formal mapping with physical processing workshops, which aligns more closely real-world green issues makes easier subsequent researchers integrate actual environments.

Язык: Английский

---

Artificial Intelligence to Solve Production Scheduling Problems in Real Industrial Settings: Systematic Literature Review

Electronics, Год журнала: 2023, Номер 12(23), С. 4732 - 4732

Опубликована: Ноя. 22, 2023

This literature review examines the increasing use of artificial intelligence (AI) in manufacturing systems, line with principles Industry 4.0 and growth smart factories. AI is essential for managing complexities modern manufacturing, including machine failures, variable orders, unpredictable work arrivals. study, conducted using Scopus Web Science databases bibliometric tools, has two main objectives. First, it identifies trends AI-based scheduling solutions most common techniques. Second, assesses real impact on production industrial settings. study shows that particle swarm optimization, neural networks, reinforcement learning are widely used techniques to solve problems. have reduced costs, increased energy efficiency, improved practical applications. increasingly critical addressing evolving challenges contemporary environments.

Язык: Английский

---

Deep reinforcement learning for solving resource constrained project scheduling problems with resource disruptions

Robotics and Computer-Integrated Manufacturing, Год журнала: 2023, Номер 85, С. 102628 - 102628

Опубликована: Авг. 21, 2023

Язык: Английский

---