Trends in Sustainable Inventory Management Practices in Industry 4.0

Processes, Journal Year: 2025, Volume and Issue: 13(4), P. 1131 - 1131

Published: April 9, 2025

This study examines 52 recently published papers on sustainable inventory management in Industry 4.0, intending to bridge theory and practice through a comprehensive literature review. By analyzing the latest advancements discussed over past two years, covering 2024 2025, we identify key trends shaping field highlight existing gaps that may require further exploration. Focusing this time frame is particularly relevant because it reflects how companies have started using artificial intelligence more practically support sustainability goals. During these AI has been applied improve tracked, demand predicted, resources are managed reduce waste. These tools making supply chains efficient while helping organizations lower their environmental impact. In regard, our work aims provide deeper understanding of strategies evolving response technological innovations, offering insights for researchers practitioners seeking enhance efficiency responsibility modern chains.

Language: Английский

---

Deploying lean six sigma and industry 4.0 framework in an auto motive manufacturing organization for establishing circular economy

OPSEARCH, Journal Year: 2025, Volume and Issue: unknown

Published: April 9, 2025

Language: Английский

---

Dynamic Cost Estimation and Optimization Strategy in Engineering Cost Combining Reinforcement Learning

Applied Mathematics and Nonlinear Sciences, Journal Year: 2025, Volume and Issue: 10(1)

Published: Jan. 1, 2025

Abstract Accurate cost estimation and optimization are crucial in engineering project management, as budget overruns resource misallocations often lead to financial operational inefficiencies. Traditional methods, including regression models heuristic approaches, struggle adapt the complex dynamic nature of projects. We proposes a reinforcement learning (RL)-based strategy that continuously refines predictions allocations. The proposed framework integrates deep learning-based model with an RL-driven strategy, enabling adaptive from historical ongoing data. A multi-objective is incorporated balance cost, quality, timeline constraints using Pareto-front analysis. RL agent learns optimal allocation policies through iterative interactions environment, improving decision-making efficiency. Experimental evaluations demonstrate RL-based outperforms conventional machine achieving lower mean absolute error root square estimation. Additionally, results average reduction approximately 7% across different categories. integration further enhances efficiency while maintaining feasibility. These findings validate approach effective solution for accuracy management.

Language: Английский

---

Model-driven deep learning for joint control and decision-making in failure-prone circular multistage manufacturing systems

International Journal of Computer Integrated Manufacturing, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 22

Published: April 23, 2025

Language: Английский

---

Optimizing quality and cost in remanufacturing under uncertainty

Production Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 5, 2024

Abstract In the context of growing sustainability demands, businesses are increasingly adapting their production practices by integrating remanufacturing. However, companies often face challenges in profitably implementing remanufacturing due to complexities arising from uncertainties processes, product quality, and market conditions. This highlights need for effective decision support processes. Addressing this challenge, our research introduces an algorithm designed identify cost-efficient process plans that optimize order fulfillment while considering a company’s specific capabilities inventory levels. By modeling planning as Markov process, comprehensively accounts both process-related quality-related uncertainties. approach enables evaluation all Pareto optimal terms cost efficiency reliability. We validate methodology through real-world application automation industry, specifically focusing on variable speed drives. case study demonstrates practical relevance potential significant reductions, enhanced efficiency, improved labor productivity. Overall, gain critical insights into financial prospects efforts, identifying opportunities optimization expansion new quality categories. enhances economic aligns with consumer preferences distinct qualities.

Language: Английский

---

A Review on Reinforcement Learning in Production Scheduling: An Inferential Perspective

Algorithms, Journal Year: 2024, Volume and Issue: 17(8), P. 343 - 343

Published: Aug. 7, 2024

In this study, a systematic review on production scheduling based reinforcement learning (RL) techniques using especially bibliometric analysis has been carried out. The aim of work is, among other things, to point out the growing interest in domain and outline influence RL as type machine scheduling. To achieve this, paper explores by investigating descriptive metadata pertinent publications contained Scopus, ScienceDirect, Google Scholar databases. study focuses wide spectrum spanning years between 1996 2024. findings can serve new insights for future research endeavors realm techniques.

Language: Английский

---