Multiagent Reinforcement Learning: Methods, Trustworthiness, Applications in Intelligent Vehicles, and Challenges DOI
Ziyuan Zhou, Guanjun Liu, Ying Tang

и другие.

IEEE Transactions on Intelligent Vehicles, Год журнала: 2024, Номер unknown, С. 1 - 23

Опубликована: Янв. 1, 2024

Multiagent Reinforcement Learning (MARL) plays a pivotal role in intelligent vehicle systems, offering solutions for complex decision-making, coordination, and adaptive behavior among autonomous agents. This review aims to highlight the importance of fostering trust MARL emphasize significance revolutionizing systems. First, this paper summarizes fundamental methods MARL. Second, it identifies limitations safety, robustness, generalization, ethical constraints outlines corresponding research methods. Then we summarize their applications Considering human interaction is essential practical various domains, also analyzes challenges associated with MARL's human-machine These challenges, when overcome, could significantly enhance real-world implementation MARL-based

Язык: Английский

Deep reinforcement learning in smart manufacturing: A review and prospects DOI
Chengxi Li, Pai Zheng, Yue Yin

и другие.

CIRP journal of manufacturing science and technology, Год журнала: 2022, Номер 40, С. 75 - 101

Опубликована: Дек. 2, 2022

Язык: Английский

Процитировано

167
A Systematic Study on Reinforcement Learning Based Applications DOI Creative Commons

Keerthana Sivamayilvelan,

R Elakkiya,

Belqasem Aljafari

и другие.

Energies, Год журнала: 2023, Номер 16(3), С. 1512 - 1512

Опубликована: Фев. 3, 2023

We have analyzed 127 publications for this review paper, which discuss applications of Reinforcement Learning (RL) in marketing, robotics, gaming, automated cars, natural language processing (NLP), internet things security, recommendation systems, finance, and energy management. The optimization use is critical today’s environment. mainly focus on the RL application Traditional rule-based systems a set predefined rules. As result, they may become rigid unable to adjust changing situations or unforeseen events. can overcome these drawbacks. learns by exploring environment randomly based experience, it continues expand its knowledge. Many researchers are working RL-based management (EMS). utilized such as optimizing smart buildings, hybrid automobiles, grids, managing renewable resources. contributes achieving net zero carbon emissions sustainable In context technology, be optimize regulation building heating, ventilation, air conditioning (HVAC) reduce consumption while maintaining comfortable atmosphere. EMS accomplished teaching an agent make judgments sensor data, temperature occupancy, modify HVAC system settings. has proven beneficial lowering usage buildings active research area buildings. used electric vehicles (HEVs) learning optimal control policy maximize battery life fuel efficiency. acquired remarkable position gaming applications. majority security-related operate simulated recommender provide good suggestions accuracy diversity. This article assists novice comprehending foundations reinforcement

Язык: Английский

Процитировано

68
Machine learning scopes on microgrid predictive maintenance: Potential frameworks, challenges, and prospects DOI
M.Y. Arafat, M. J. Hossain, Md Morshed Alam

и другие.

Renewable and Sustainable Energy Reviews, Год журнала: 2023, Номер 190, С. 114088 - 114088

Опубликована: Ноя. 16, 2023

Язык: Английский

Процитировано

49
Paradigm Shift for Predictive Maintenance and Condition Monitoring from Industry 4.0 to Industry 5.0: A Systematic Review, Challenges and Case Study DOI Creative Commons

Aitzaz Ahmed Murtaza,

Amina Saher,

Muhammad Hamza Zafar

и другие.

Results in Engineering, Год журнала: 2024, Номер unknown, С. 102935 - 102935

Опубликована: Сен. 1, 2024

Язык: Английский

Процитировано

28
Reinforcement and deep reinforcement learning-based solutions for machine maintenance planning, scheduling policies, and optimization DOI
Oluwaseyi Ogunfowora, Homayoun Najjaran

Journal of Manufacturing Systems, Год журнала: 2023, Номер 70, С. 244 - 263

Опубликована: Авг. 5, 2023

Язык: Английский

Процитировано

43
A Review of Deep Reinforcement Learning Approaches for Smart Manufacturing in Industry 4.0 and 5.0 Framework DOI Creative Commons
Alejandro J. del Real, Doru Stefan Andreiana, Álvaro Ojeda Roldán

и другие.

Applied Sciences, Год журнала: 2022, Номер 12(23), С. 12377 - 12377

Опубликована: Дек. 3, 2022

In this review, the industry’s current issues regarding intelligent manufacture are presented. This work presents status and potential for I4.0 I5.0’s revolutionary technologies. AI and, in particular, DRL algorithms, which a perfect response to unpredictability volatility of modern demand, studied detail. Through introduction RL concepts development those with ANNs towards DRL, variety these kinds algorithms highlighted. Moreover, because data based, their modification meet requirements industry operations is also included. addition, review covers inclusion new concepts, such as digital twins, an absent environment model how it can improve performance application even more. highlights that applicability demonstrated across all manufacturing operations, outperforming conventional methodologies most notably, enhancing process’s resilience adaptability. It stated there still considerable be carried out both academia fully leverage promise disruptive tools, begin deployment industry, take step closer I5.0 industrial revolution.

Язык: Английский

Процитировано

41
Q-learning driven multi-population memetic algorithm for distributed three-stage assembly hybrid flow shop scheduling with flexible preventive maintenance DOI
Yanhe Jia, Qi Yan, Hongfeng Wang

и другие.

Expert Systems with Applications, Год журнала: 2023, Номер 232, С. 120837 - 120837

Опубликована: Июнь 19, 2023

Язык: Английский

Процитировано

40
Machine Learning in Manufacturing towards Industry 4.0: From ‘For Now’ to ‘Four-Know’ DOI Creative Commons
Tingting Chen, Vignesh Sampath, Marvin Carl May

и другие.

Applied Sciences, Год журнала: 2023, Номер 13(3), С. 1903 - 1903

Опубликована: Фев. 1, 2023

While attracting increasing research attention in science and technology, Machine Learning (ML) is playing a critical role the digitalization of manufacturing operations towards Industry 4.0. Recently, ML has been applied several fields production engineering to solve variety tasks with different levels complexity performance. However, spite enormous number use cases, there no guidance or standard for developing solutions from ideation deployment. This paper aims address this problem by proposing an application roadmap industry based on state-of-the-art published topic. First, presents two dimensions formulating tasks, namely, ’Four-Know’ (Know-what, Know-why, Know-when, Know-how) ’Four-Level’ (Product, Process, Machine, System). These are used analyze development trends manufacturing. Then, provides implementation pipeline starting very early stages solution summarizes available methods, including supervised learning semi-supervised unsupervised reinforcement along their typical applications. Finally, discusses current challenges during applications outline possible directions future developments.

Язык: Английский

Процитировано

38
Dynamic maintenance scheduling approach under uncertainty: Comparison between reinforcement learning, genetic algorithm simheuristic, dispatching rules DOI Creative Commons
Marcelo Luis Ruiz-Rodríguez, Sylvain Kubler,

Jérémy Robert

и другие.

Expert Systems with Applications, Год журнала: 2024, Номер 248, С. 123404 - 123404

Опубликована: Фев. 8, 2024

Maintenance planning and scheduling are an essential part of manufacturing companies to prevent machine breakdowns increase uptime, along with production efficiency. One the biggest challenges is effectively address uncertainty (e.g., unexpected failures, variable time repair). Multiple approaches have been used solve maintenance problem, including dispatching rules (DR), metaheuristics simheuristics, or most recently reinforcement learning (RL). However, best our knowledge, no study has ever studied what extent these techniques effective when faced different levels uncertainty. To overcome this gap in research, paper presents approach by analyzing impact categorized uncertainty, specifically high low, on failure distribution repair. Upon formalization experiments conducted performed simulated scenarios degrees also considering a real-life use case. The results indicate that rescheduling based genetic algorithm (GA) simheuristic outperforms RL DR terms total but not mean repair configured re-optimization frequencies (i.e., hourly re-optimization), rapidly underperforms frequency decreases. Furthermore, demonstrates GA-simheuristic highly computationally demanding compared rule-based policies.

Язык: Английский

Процитировано

13
A Comprehensive Survey on Deep Learning-based Predictive Maintenance DOI
Uzair Farooq Khan, Dong Seon Cheng, Francesco Setti

и другие.

ACM Transactions on Embedded Computing Systems, Год журнала: 2025, Номер unknown

Опубликована: Апрель 24, 2025

With the advent of Industrial 4.0 and push towards Industry 5.0, data generated by industries have become surprisingly large. This abundance significantly boosts machine deep learning models for Predictive Maintenance (PdM). The PdM plays a vital role in extending lifespan industrial equipment machines while also helping to reduce risk unscheduled downtime. Given its multidisciplinary nature, field has been approached from many different angles: this comprehensive survey aims provide an up-to-date overview focused on all learning-based strategies, discussing weaknesses strengths. is based Preferred Reporting Items Systematic Reviews Meta-Analyses (PRISMA) methodological flow, allowing systematic complete review literature. In particular, firstly, we explore main used PdM, mainly Convolutional Neural Networks (ConvNets), Autoencoders (AEs), Generative Adversarial (GANs), Transformers, giving newest such as diffusion foundation models. Then, discuss paradigms applied i.e. , supervised, unsupervised, ensemble, transfer, federated, reinforcement learning. Furthermore, work discusses pipeline data-driven benefits, practical applications, datasets, benchmarks. addition, evaluation metrics each stage state-of-the-art hardware devices are discussed. Finally, challenges future presented.

Язык: Английский

Процитировано

1