Published 2026-05-27
Keywords
- Deep Reinforcement Learning,
- Smart Manufacturing,
- Process Optimization,
- Machine Learning,
- Industrial Automation
- Artificial Intelligence,
- Supply Chain Management,
- Energy Consumption,
- Quality Control,
- IoT,
- Edge Computing ...More
How to Cite
Copyright (c) 2026 Swami Vivekananda University Press
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Abstract
Smart manufacturing represents a paradigm shift in the industrial sector, where advanced technologies such as Artificial Intelligence (AI), Internet of Things (IoT), and Big Data are combined to optimize manufacturing processes. One of the most promising technologies in this context is Deep Reinforcement Learning (DRL), which has the potential to significantly enhance decision-making in complex manufacturing systems. DRL, a combination of deep learning and reinforcement learning, can enable machines to learn optimal decision policies through interactions with dynamic environments, making it particularly suitable for optimizing manufacturing processes.
In this paper, we explore the application of DRL to optimize various stages of the manufacturing process, including production scheduling, supply chain management, energy consumption, and quality control. We review existing literature on DRL applications in manufacturing and highlight key challenges, including the high computational cost of training DRL models and the need for vast amounts of data to train these models effectively. Additionally, we investigate the integration of DRL with other emerging technologies such as IoT for real-time data collection and edge computing for low-latency decision making. The paper proposes a framework for implementing DRL-based optimization in smart manufacturing systems and discusses potential areas for future research, including transfer learning and multi-agent systems. By leveraging the power of DRL, manufacturers can achieve more efficient operations, reduced waste, and improved overall system performance.
The potential impact of DRL on smart manufacturing is vast, with applications ranging from predictive maintenance to autonomous decision-making. This paper contributes to the growing body of research on the intersection of AI and manufacturing by providing insights into the practical implementation of DRL for process optimization and offering directions for future exploration.
DOI - https://doi.org/10.65525/SVUP.9788199778009.2026.53-59