STEMM Institute Press
Science, Technology, Engineering, Management and Medicine
From Manual to Intelligent: Large AI Models Reshaping Industrial Inspection Paradigms
DOI: https://doi.org/10.62517/jike.202504308
Author(s)
Fanghui Li1, Jia Li2,3,*
Affiliation(s)
1Machinery Industry Information Research Institute, Beijing, China 2China Electronics Standardization Institute, Beijing, China 3Beijing University of Technology, Beijing, China *Corresponding Author
Abstract
Industrial inspection, a core component of manufacturing quality control, is undergoing a profound transformation driven by artificial intelligence (AI), particularly multimodal large models. The study systematically examines the technological evolution of AI-enabled industrial inspection. It evaluates its contributions to efficiency improvement, accuracy enhancement, cost optimization, and process restructuring from the dual perspectives of “value creation” and “potential risks.” Key challenges related to data security, model reliability, deployment costs, and talent shortages are also identified. On this basis, targeted development strategies are proposed across technological, economic, human resource, and standardization dimensions. The study aims to provide both theoretical support and practical guidance for implementing large AI models in industrial inspection and promoting industrial upgrading.
Keywords
Large AI Models; Industrial Inspection; Technological Paradigm Shift; Implementation Framework
References
[1] Yan W , Fan W .Research on the Current Situation and Development of Intelligent Precision Fertilizer Technology[C]//IFIP WG International Conference on Computer and Computing Technologies in Agricultur.2019. [2] Sun, H., Teo, W., Wong, K., Dong, B., Polzer, J., & Xu, X. (2024). Automating Quality Control on a Shoestring, a Case Study. Machines. [3] Nguyen, T., Nguyen, P., & Cao, H. (2024). XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach. Inf. Fusion, 116, 102782. [4] Schraml, D., & Notni, G. (2024). Synthetic Training Data in AI-Driven Quality Inspection: The Significance of Camera, Lighting, and Noise Parameters. Sensors (Basel, Switzerland), 24. [5] Schmitt, J., Bönig, J., Borggräfe, T., Beitinger, G., & Deuse, J. (2020). Predictive model-based quality inspection using Machine Learning and Edge Cloud Computing. Adv. Eng. Informatics, 45, 101101. [6] Sundaram, S., & Zeid, A. (2023). Artificial Intelligence-Based Smart Quality Inspection for Manufacturing. Micromachines, 14. [7] Li, S., Lin, X., Xu, W., & Li, J. (2024). AI-Generated Content-Based Edge Learning for Fast and Efficient Few-Shot Defect Detection in IIoT. IEEE Transactions on Services Computing, 17, 3140-3153. [8] Li, S., Sun, W., Liang, Q., Sun, J., & Liu, C. (2025). Multimodal Fabric Defect Classification Using Channel Switching and Multiscale Feature Fusion. IEEE Transactions on Instrumentation and Measurement, 74, 1-12. [9] Zant, C., Charrier, Q., Benfriha, K., & Men, P. (2021). Enhanced Manufacturing Execution System “MES” Through a Smart Vision System. Lecture Notes in Mechanical Engineering. [10] Tantithamthavorn, C., McIntosh, S., Hassan, A., & Matsumoto, K. (2018). The Impact of Automated Parameter Optimization on Defect Prediction Models. IEEE Transactions on Software Engineering, 45, 683-711. [11] Luculescu, M., Cristea, L., & Boer, A. (2025). Artificial Vision System for Autonomous Mobile Platform Used in Intelligent and Flexible Indoor Environment Inspection. Technologies. [12] Zou, Y., Hou, R., Zhang, Y., Liu, J., Zhang, Z., & Xue, W. (2025). Research on key technologies of power substation inspection based on large model. , 13552, 135520I - 135520I-7. [13] Byun, M., Low, M., & Lin, D. (2024). A Multi-Modal AI Inspection System for Laser Labels. TENCON 2024 - 2024 IEEE Region 10 Conference (TENCON), 948-951. [14] Li, L., Ota, K., & Dong, M. (2018). Deep Learning for Smart Industry: Efficient Manufacture Inspection System With Fog Computing. IEEE Transactions on Industrial Informatics, 14, 4665-4673. [15] Mohan, V. (2025). Integrated AI Models for Simultaneous Quality Improvement and Risk Reduction in Production Processes. Journal of Information Systems Engineering and Management. [16] Yang, J., Fu, G., Zhu, W., Cao, Y., Cao, Y., & Yang, M. (2020). A Deep Learning-Based Surface Defect Inspection System Using Multiscale and Channel-Compressed Features. IEEE Transactions on Instrumentation and Measurement, 69, 8032-8042. [17] Tanisha, J., Rajesh, P., Singh, R., Adhip, K., Stuti, K., & Ajitha, D. (2024). Privacy and data protection challenges in industry 4.0: An AI-driven perspective. World Journal of Advanced Engineering Technology and Sciences. [18] Pei, J., Wang, R., Yan, P., & Tan, Y. (2025). Quality management in supply chain: Strategic implications and the paradox of AI inspection. Decision Sciences. [19] Kilsby, P., & Kun, L. (2024). Enabling Intelligent Robotic Visual Inspection in the Railway Industry with Generative AI. 2024 Eighth IEEE International Conference on Robotic Computing (IRC), 275-277. [20] Kwak, J. (2025). Developing Multidisciplinary Talent for the AI Industry: Key Factors and Strategies. Asia-pacific Journal of Convergent Research Interchange. [21] Khanam, R., Hussain, M., Hill, R., & Allen, P. (2024). A Comprehensive Review of Convolutional Neural Networks for Defect Detection in Industrial Applications. IEEE Access, 12, 94250-94295.
Copyright @ 2020-2035 STEMM Institute Press All Rights Reserved