Reshoring Decisions in Supply Chains and Industry 5.0 Optimization: AI Based Sustainable Decision Support Model DOI
Muhammet Mustafa Akkan

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Апрель 2, 2025

Abstract Global supply chains face increasingly uncertain phenomena and reshoring decisions have become a strategic necessity. This paper presents an artificial intelligence-based decision support model for optimizing processes in connection with sustainability Industry 5.0 principles. The developed supports multidimensional decision-making chain management by using big data analytics, machine learning optimization techniques. proposed framework evaluates critical factors such as lead time, cost, operational risks, environmental impact, resilience integrated approach. Combining different sources, the allows makers to determine most appropriate strategies conducting dynamic scenario analyses. approach, which adopts human-machine collaboration approach of 5.0, not only increases economic efficiency, but also contributes principles sustainable production management. With study, it is aimed make significant contributions academic literature industrial applications presenting new perspective on decisions.

Язык: Английский

Review of manufacturing system design in the interplay of Industry 4.0 and Industry 5.0 (Part II): Design processes and enablers DOI
Jiewu Leng,

Jun‐feng Guo,

Junxing Xie

и другие.

Journal of Manufacturing Systems, Год журнала: 2025, Номер 79, С. 528 - 562

Опубликована: Фев. 19, 2025

Язык: Английский

Процитировано

3
Effect of blockchain on corporate social responsibility in supply chain management DOI
Kai Kang, Bing Qing Tan, Felix T.S. Chan

и другие.

International Journal of Production Research, Год журнала: 2025, Номер unknown, С. 1 - 27

Опубликована: Март 10, 2025

Язык: Английский

Процитировано

2
Bridging Industry 5.0 and Agriculture 5.0: Historical Perspectives, Opportunities, and Future Perspectives DOI Open Access

Doha Haloui,

Kenza Oufaska, Mustapha Oudani

и другие.

Sustainability, Год журнала: 2024, Номер 16(9), С. 3507 - 3507

Опубликована: Апрель 23, 2024

The agricultural industry has undergone several significant changes over the past few centuries, influenced by industrial revolutions that have occurred. These progressed from Indigenous agriculture to mechanized farming and current precision agriculture. While model increased output, it also faced various challenges in recent years. Industry 5.0 is expected a impact on sector potentially lead fifth revolution. In this paper, we examine motivation behind 4.0 5.0, review phases of these occurred so far, offer suggestions for future. We provide an overview concepts as well Agriculture discuss smart strategies are being implemented different countries advance sectors. Additionally, focus potential applications technologies research associated with them. Our goal professionals new opportunities.

Язык: Английский

Процитировано

14
Federated learning-empowered smart manufacturing and product lifecycle management: A review DOI
Jiewu Leng, Richard Li,

Junxing Xie

и другие.

Advanced Engineering Informatics, Год журнала: 2025, Номер 65, С. 103179 - 103179

Опубликована: Фев. 10, 2025

Язык: Английский

Процитировано

1
Industry 5.0: a review of emerging trends and transformative technologies in the next industrial revolution DOI

Tarun Rijwani,

Soni Kumari, R. Srinivas

и другие.

International Journal on Interactive Design and Manufacturing (IJIDeM), Год журнала: 2024, Номер unknown

Опубликована: Июнь 18, 2024

Язык: Английский

Процитировано

7
Edge-cloud collaboration-driven predictive planning based on LSTM-attention for wastewater treatment DOI
Shuaiyin Ma, Wei Ding,

Yujuan Zheng

и другие.

Computers & Industrial Engineering, Год журнала: 2024, Номер 195, С. 110425 - 110425

Опубликована: Июль 27, 2024

Язык: Английский

Процитировано

6
Intelligent Manufacturing from the Perspective of Industry 5.0: Application Review and Prospects DOI Creative Commons

Zi'ang Lei,

Jianhua Shi, Ziren Luo

и другие.

IEEE Access, Год журнала: 2024, Номер 12, С. 167436 - 167451

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

6
The research landscape of industry 5.0: a scientific mapping based on bibliometric and topic modeling techniques DOI Creative Commons
Abderahman Rejeb, Karim Rejeb, Imen Zrelli

и другие.

Flexible Services and Manufacturing Journal, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 30, 2024

Abstract Industry 5.0 (I5.0) marks a transformative shift toward integrating advanced technologies with human-centric design to foster innovation, resilient manufacturing, and sustainability. This study aims examine the evolution collaborative dynamics of I5.0 research through bibliometric analysis 942 journal articles from Scopus database. Our findings reveal significant increase in research, particularly post-2020, yet highlight fragmented collaboration networks noticeable gap between institutions developed developing countries. Key thematic areas identified include human-robot collaboration, data management security, AI-driven sustainable practices. These insights suggest that more integrated approach is essential for advancing I5.0, calling strengthened global collaborations balanced emphasis on both technological elements fully realize its potential driving industrial provides first comprehensive offering valuable researchers practitioners.

Язык: Английский

Процитировано

6
Digital Twin-Driven Multi-Factor Production Capacity Prediction for Discrete Manufacturing Workshop DOI Creative Commons

Hu Cai,

Jiafu Wan, Baotong Chen

и другие.

Applied Sciences, Год журнала: 2024, Номер 14(7), С. 3119 - 3119

Опубликована: Апрель 8, 2024

Traditional capacity forecasting algorithms lack effective data interaction, leading to a disconnection between the actual plan and production. This paper discusses multi-factor model based on discrete manufacturing workshop proposes digital twin-driven prediction method. Firstly, this gives system framework for production in workshops twins. Then, mathematical is described under multiple disturbance factors. Furthermore, an innovative method, using “digital twin + Long-Short-Term Memory Network (LSTM) algorithm”, presented. Finally, platform deployed commemorative disk custom line as prototype platform. The verification shows that proposed method can achieve accuracy rate of 91.8% capacity. By integrating optimization feedback function into process control, enables accurate perception current state future changes system, effectively evaluating delivery date workshops.

Язык: Английский

Процитировано

4
A hybrid LSTM random forest model with grey wolf optimization for enhanced detection of multiple bearing faults DOI Creative Commons
Said Djaballah, Lotfi Saïdi, Kamel Meftah

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Окт. 14, 2024

Bearing degradation is the primary cause of electrical machine failures, making reliable condition monitoring essential to prevent breakdowns. This paper presents a novel hybrid model for detection multiple faults in bearings, combining Long Short-Term Memory (LSTM) networks with random forest (RF) classifiers, further enhanced by Grey Wolf Optimization (GWO) algorithm. The proposed approach structured three stages: first, time and frequency domain features are manually extracted from vibration signals; second, these processed dual-layer LSTM network, which specifically designed capture complex temporal relationships within data; finally, GWO algorithm employed optimize feature selection outputs, feeding most relevant into RF classifier fault classification. was rigorously evaluated using dataset comprising six distinct bearing health conditions: healthy, outer race fault, ball inner compounded generalized degradation. LSTM-RF-GWO achieved remarkable classification accuracy 98.97%, significantly outperforming standalone models such as (93.56%) (98.44%). Furthermore, inclusion led an additional improvement 0.39% compared LSTM-RF without optimization. Other performance metrics, including precision, kappa coefficient, false negative rate (FNR), positive (FPR), were also improved, precision reaching 99.28% coefficient achieving 99.13%. FNR FPR reduced 0.0071 0.0015, respectively, underscoring model's effectiveness minimizing misclassifications. experimental results demonstrate that framework not only enhances but provides robust solution distinguishing between closely related conditions, it valuable tool predictive maintenance industrial applications.

Язык: Английский

Процитировано

4