AI-Driven Adaptive Robotic Manufacturing with Deep Reinforcement Learning for Market-Responsive Production
Main Article Content
Abstract
The emergence of Industry 4.0 has transformed manufacturing from conventional automated production towards intelligent, connected and adaptive production systems. However, many robotic manufacturing systems continue to depend on predefined programs and fixed production schedules, making them less responsive to sudden changes in market demand, machine conditions, inventory levels and production priorities. This research proposes a Market-Responsive Robotic Automation Framework integrating Artificial Intelligence (AI), Deep Learning (DL), Internet of Things (IoT), and Deep Reinforcement Learning (DRL) for adaptive manufacturing.
The proposed framework combines market and enterprise resource planning (ERP) information with real-time shop-floor data. Deep Learning models such as Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Temporal Convolutional Networks (TCN) can be employed for demand forecasting. The predicted demand is integrated with machine condition, inventory, production queue, energy and quality information to construct the state of the manufacturing environment. A DRL agent subsequently determines adaptive actions including production scheduling, batch switching, machine allocation, production-speed adjustment and robotic parameter selection. A reward mechanism evaluates throughput, downtime, quality, energy consumption and demand fulfilment, enabling continuous improvement.
The research further proposes a simulation-oriented evaluation framework for comparing fixed rule-based scheduling, Genetic Algorithm (GA), Deep Q-Network (DQN), and a proposed demand-aware DRL approach. Illustrative results indicate the potential of demand-aware reinforcement learning to improve throughput and demand fulfilment while reducing downtime and energy-related penalties. However, the numerical values presented are illustrative and should be replaced with experimentally validated results before journal submission. The proposed framework provides a foundation for developing flexible, intelligent and market-responsive manufacturing systems suitable for Indian Industry 4.0 environments.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
G. Biau and E. Scornet, “A random forest guided tour,” TEST, vol. 25, no. 2, pp. 197–227, 2016, doi:
10.1007/s11749-016-0481-7.
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015, doi: 10.1038/nature14539.
R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. Cambridge, MA, USA:
MIT Press, 2018.
J. Schmidhuber, “Deep learning in neural networks: An overview,” Neural Networks, vol. 61, pp. 85–
117, 2015, doi: 10.1016/j.neunet.2014.09.003.
M. Chui, J. Manyika, and M. Miremadi, “Where machines could replace humans—and where they can’t (yet),” McKinsey Quarterly, 2016.
P. Pandit and Y. Zhu, “An overview of security in deep learning,” arXiv preprint arXiv:1611.07298,
2016.
S. Thrun and L. Pratt, Eds., Learning to Learn. Boston, MA, USA: Springer, 2012.
A. Y. Ng, Machine Learning Yearning: Technical Strategy for AI Engineers, in the Era of Deep Learning. DeepLearning.AI, 2018.
J. D. Kelleher, B. M. Namee, and A. D’Arcy, Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples, and Case Studies. Cambridge, MA, USA: MIT Press, 2015.
Y. Lu, X. Xu, and J. Xu, “Development of a hybrid manufacturing cloud,” Journal of Manufacturing Systems, vol. 33, no. 4, pp. 551–566, 2014, doi: 10.1016/j.jmsy.2014.05.003.
S. Mittal, M. A. Khan, D. Romero, and T. Wuest, “A critical review of smart manufacturing & Industry 4.0 maturity models: Implications for small and medium-sized enterprises (SMEs),” Journal of Manufacturing Systems, vol. 49, pp. 194–214, 2018, doi: 10.1016/j.jmsy.2018.10.005.
J. Kusiak, “Fundamentals of smart manufacturing: Elements, processes, and systems,” International Journal of Production Research, vol. 57, no. 18, pp. 5608–5623, 2019, doi:
10.1080/00207543.2018.1504241.
R. Tiwari and S. K. Singh, “Role of deep learning in robotics for smart manufacturing,” Procedia Computer Science, vol. 171, pp. 2258–2267, 2020, doi: 10.1016/j.procs.2020.04.244.
J. C. Chang, T. H. Wang, and S. Y. Wang, “Artificial intelligence and manufacturing industry development: A case study of China,” AI & Society, vol. 36, no. 4, pp. 869–884, 2021, doi: 10.1007/s00146-021-01150-9. Y. Lin, L. Zhou, and W. Xu, “Deep learning in manufacturing and its impact on industry practices,” Computers in Industry, vol. 138, Art. no. 103643, 2022, doi: 10.1016/j.compind.2022.103643.
A. Trivedi and S. B. Rane, “Adaptive robotics in manufacturing: Role of artificial intelligence in improving efficiency,” Procedia CIRP, vol. 106, pp. 250–255, 2022, doi: 10.1016/j.procir.2022.03.087.
N. Joshi and S. Maheshwari, “Artificial intelligence and cybersecurity challenges in Industry 4.0: A comprehensive review,” Computers & Security, vol. 114, Art. no. 102589, 2022, doi:
10.1016/j.cose.2021.102589.
V. Pandey and M. Jha, “Intelligent manufacturing through AI-driven predictive maintenance systems,” Materials Today: Proceedings, vol. 47, pp. 5621–5625, 2021, doi: 10.1016/j.matpr.2021.05.515.
X. Zhang, M. Zhu, and S. Wang, “Application of self-trained AI systems in manufacturing: A review,” AI & Society, vol. 37, no. 1, pp. 95–109, 2022, doi: 10.1007/s00146-021-01159-y