Edge-Based AIGC Framework for Smart Manufacturing: Lightweight Visual Generation and Industrial Knowledge Integration
Keywords:
edge computing, smart manufacturing, AI-generated content, visual generation, model compression, industrial knowledge graph, system governanceAbstract
The convergence of artificial intelligence generated content and edge computing holds transformative potential for smart manufacturing, enabling real-time visual decision support, defect detection, and human-machine collaboration directly at the production line. However, deploying generative models in edge environments poses severe system-level challenges related to computational constraints, latency, data heterogeneity, and integration with industrial domain knowledge. This paper presents a comprehensive framework for edge-based AI-generated content systems tailored to smart manufacturing, emphasizing the co-design of lightweight visual generation models and industrial knowledge integration mechanisms. We examine the architectural trade-offs involved in distributing generative inference across edge-cloud continuums, discuss model compression strategies that preserve output quality under resource limitations, and analyze the role of semantic alignment techniques that link generated visuals with structured manufacturing ontologies and operational knowledge graphs. The framework extends beyond technical components to address governance, robustness, and sustainability concerns that arise when generative models are embedded in safety-critical production environments. By articulating structural interdependencies between model design, knowledge orchestration, and infrastructure policy, the paper offers a holistic systems perspective on how edge-native generative intelligence can be realized in practice. Governance considerations such as data sovereignty, continuous model validation, and fairness across heterogeneous shop floors are discussed in depth. The analysis reveals that successful deployment requires navigating complex trade-offs between model fidelity, inference latency, and energy efficiency, while maintaining the capacity to incorporate evolving domain knowledge without catastrophic forgetting. The discussion synthesizes insights from distributed systems, industrial informatics, and socio-technical research, providing a roadmap for future work in building resilient, interpretable, and ethically grounded generative systems for the factory of the future.
References
1. Lee, J., Bagheri, B., & Kao, H. A. (2015). A cyber-physical systems architecture for Industry 4.0-based manufacturing systems. Manufacturing Letters, 3, 18–23.
2. Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016). Edge computing: Vision and challenges. IEEE Internet of Things Journal, 3(5), 637–646.
3. Cao, Y., Li, S., Liu, Y., Yan, Z., Dai, Y., Yu, P. S., & Sun, L. (2023). A comprehensive survey of AI-generated content (AIGC): A history of generative AI from GAN to ChatGPT. arXiv preprint arXiv:2303.04226.
4. Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., ... & Liang, P. (2021). On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258.
5. Dong, X. L., Gabrilovich, E., Heitz, G., Horn, W., Lao, N., Murphy, K., ... & Zhang, W. (2014). Knowledge vault: A web-scale approach to probabilistic knowledge fusion. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 601–610). ACM.
6. Han, S., Mao, H., & Dally, W. J. (2016). Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. In International Conference on Learning Representations (ICLR).
7. Chen, C., Wang, C., Li, Y., Wan, Z., Geng, M., Xiao, J., ... & Peng, Y. (2026). JuZhou 1.0 Technical Report: The First Edge-Native Text-to-Image Foundation Model Trained Entirely on China-Developed AI Accelerators. arXiv preprint arXiv:2606.28421.
8. Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020). Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 37(3), 50–60.
9. Schwartz, R., Dodge, J., Smith, N. A., & Etzioni, O. (2020). Green AI. Communications of the ACM, 63(12), 54–63.
10. Zuboff, S. (2019). The age of surveillance capitalism: The fight for a human future at the new frontier of power. PublicAffairs.
11. Autor, D. H., Levy, F., & Murnane, R. J. (2003). The skill content of recent technological change: An empirical exploration. The Quarterly Journal of Economics, 118(4), 1279–1333.
12. ISO/IEC JTC 1/SC 42. (2022). ISO/IEC 22989:2022 Artificial intelligence — Concepts and terminology. International Organization for Standardization.
13. Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., ... & Liu, P. J. (2020). Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140), 1–67.
14. Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
15. Sheller, M. J., Edwards, B., Reina, G. A., Martin, J., Pati, S., Kotrotsou, A., ... & Bakas, S. (2020). Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data. Scientific Reports, 10(1), 12598.
16. Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., ... & Chen, T. (2018). Recent advances in convolutional neural networks. Pattern Recognition, 77, 354–377.
17. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). ACM.
18. Kusiak, A. (2017). Smart manufacturing. International Journal of Production Research, 56(1-2), 508–517.
19. Tao, F., Cheng, J., Qi, Q., Zhang, M., Zhang, H., & Sui, F. (2018). Digital twin-driven product design, manufacturing and service with big data. The International Journal of Advanced Manufacturing Technology, 94(9-12), 3563–3576.
20. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems (pp. 5998–6008).
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Data Intelligence and AI Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
