Research Review on AI-Enhanced Machine Vision and Robotics for Predictive Maintenance & Quality Inspection in Automated Manufacturing
Main Article Content
Abstract
With automated manufacturing advancing toward high precision and high efficiency, the integration of artificial intelligence, machine vision and industrial robots has become the core pillar of intelligent manufacturing. Traditional manual inspection and scheduled maintenance suffer from high missing detection rates, delayed response and excessive operating costs, failing to satisfy strict quality control standards of modern manufacturing. Deep learning empowers machine vision to extract defect features and realize automatic classification efficiently, while industrial robots break free from fixed programming to achieve autonomous perception and decision-making. Supported by multi-sensor data fusion and machine learning, predictive maintenance enables early equipment fault identification and drastically cuts unplanned downtime. Vision-guided robotic inspection systems outperform human operators in both detection speed and precision. This paper systematically sorts out technical routes, system architectures and engineering practices of the two major application scenarios, and discusses cutting-edge directions for collaborative integration of vision and robotic technologies, providing systematic references for engineering implementation and relevant research layout.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
Y. Liang, S. Feng, Y. Zhang, et al., “A stable diffusion enhanced YOLOV5 model for metal stamped part defect detection based on improved network structure,” J. Manuf. Processes, vol. 111, pp. 21–31, 2024, doi: 10.1016/J. JMAPRO.2023.12.064.
H. Fang, S. Ong, and A. Nee, “Robot path planning optimization for welding complex joints,” Int. J. Adv. Manuf. Technol., vol. 90, nos. 9–12, pp. 3829–3839, 2017, doi: 10.1007/s00170-016-9684-z.
D. Kiefer, F. Grimm, T. Straub, et al., “Enhancing power skiving tool longevity: The synergy of AI and robotics in manufacturing automation,” Int. J. Mechatronics Manuf. Syst., vol. 17, no. 2, pp. 201–224, 2024, doi: 10.1504/IJMMS.2024.143059.
D. Kumar, R. S. Addula, M. Lind, et al., “AI-driven hybrid deep learning and swarm intelligence for predictive maintenance of smart manufacturing robots in Industry 4.0,” Electronics, vol. 15, no. 3, p. 715, 2026, doi: 10.3390/ELECTRONICS15030715.
I. Yousif, L. Burns, E. F. Kalach, et al., “Leveraging computer vision towards high-efficiency autonomous industrial facilities,” J. Intell. Manuf., vol. 36, no. 5, pp. 1–26, 2024, doi: 10.1007/S10845-024-02396-1.
M. O. Matamoros, T. G. J. Nava, M. J. J. Escobar, et al., “Artificial intelligence for quality defects in the automotive industry: A systemic review,” Sensors, vol. 25, no. 5, p. 1288, 2025, doi: 10.3390/S25051288.
A. Victor, G. Anna, and L. Yvonne, “Lessons from adopting robotic in-line quality inspection in the Swedish manufacturing industry,” Procedia Comput. Sci., vol. 217, pp. 386–394, 2023, doi: 10.1016/J.PROCS.2022.12.234.
A. Chaabani, R. Cherif, and Y. Yaddaden, “Automating quality control: Real-time defect detection and automated decision-making with AI and Doosan robotics,” Int. J. Intell. Robot. Appl., vol. 9, no. 3, pp. 1–15, 2025, doi: 10.1007/S41315-024-00417-Z.
L. Patrício, L. Varela, and Z. Silveira, “Proposal for a sustainable model for integrating robotic process automation and machine learning in failure prediction and operational efficiency in predictive maintenance,” Appl. Sci., vol. 15, no. 2, p. 854, 2025, doi: 10.3390/APP15020854.
Y. D. Patrashko and V. Gurau, “Machine learning-powered vision for robotic inspection in manufacturing: A review,” Sensors, vol. 26, no. 3, p. 788, 2026, doi: 10.3390/S26030788.
A. Mahajan, G. Singh, S. Devgan, et al., “Next-generation manufacturing: Leveraging AI for industrial innovation and growth,” Comput. Ind. Eng., vol. 211, p. 111618, 2026, doi: 10.1016/J.CIE.2025.111618.
C. L. Wang, “Research on intelligent technology in mechanical design, manufacturing and automation,” China Strategic Emerging Industries, no. 8, pp. 63–65, 2026.
Y. Q. Sun and T. Shen, “Research on application of industrial robot vision systems in electrical automation,” China Equipment Eng., no. 6, pp. 28–30, 2026.
C. B. Li, “Application of machine vision in machinery manufacturing automation,” Paper and Paper Making Equipment & Materials, vol. 54, no. 11, pp. 88–90, 2025.
T. Yue, “Artificial intelligence in metallurgical automation production— Comment on complex metallurgical process intelligent control,” China Nonferrous Metallurgy, vol. 53, no. 4, pp. 161–162, 2024.
“Robotics; findings from Singapore National University in the area of robotics reported (Robot path planning optimization for welding complex joints),” J. Robotics & Machine Learning, p. 34, 2017.