EVALUATION OF THE METROLOGICAL CHARACTERISTICS OF AI-BASED OPTICAL INSPECTION SYSTEMS AND DEVELOPMENT OF THEIR MEASUREMENT UNCERTAINTY BUDGET

Authors

  • A.A. Abdumalikov State Institution “Uzbekistan Scientific Testing and Quality Control Center” Author
  • D.U. Tojaliyev Fergana State Technical University, Department of Light Industry Engineering Author
  • U.S.Quryazov Urganch State University Author

Keywords:

metrological assurance, optical inspection system, artificial intelligence, measurement uncertainty, validation, calibration, knitted fabric, metrological passport

Abstract

The paper addresses the metrological assurance of AI-based optical inspection systems that detect surface defects of knitted fabric in real time, treating them as measuring and control instruments. Analytical relationships between the measurement range, spatial resolution, exposure time and frame rate are derived, and their nominal values are formalised as a metrological passport. Following the GUM principles, an uncertainty budget comprising type A and type B sources was compiled; the expanded uncertainty was found to be U = ±0.031 (on the F1 scale, k = 2). A procedure for initial validation and periodic calibration of the system is proposed.

References

1.Decree of the President of the Republic of Uzbekistan No. PF–6199 of 26 March 2021 “On the Strategy for the Comprehensive Development of the Light Industry for 2021–2025”.

2.Decree of the President of the Republic of Uzbekistan No. PF–71 of 1 May 2024 “On Measures to Support Enterprises Operating in Textile and Garment-Knitwear Industry Zones”.

3.O‘z DSt ISO/IEC 17025. General requirements for the competence of testing and calibration laboratories. – Tashkent: Uzstandard Agency.

4.Ngan H.Y.T., Pang G.K.H., Yung N.H.C. Automated fabric defect detection – A review // Image and Vision Computing. – 2011. – Vol. 29, № 7. – P. 442–458.

5.Hanbay K., Talu M.F., Özgüven Ö.F. Fabric defect detection systems and methods – A systematic literature review // Optik. – 2016. – Vol. 127, № 24. – P. 11960–11973.

6.Redmon J., Divvala S., Girshick R., Farhadi A. You only look once: unified, real-time object detection // Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). – 2016. – P. 779–788.

7.Jocher G., Chaurasia A., Qiu J. Ultralytics YOLOv8 [Electronic resource]. – 2023. – URL: https://github.com/ultralytics/ultralytics.

8.O‘z DSt ISO 9001:2015. Quality management systems. Requirements. – Tashkent: Uzstandard Agency.

9.ISO/IEC Guide 98-3:2008. Uncertainty of measurement – Part 3: Guide to the expression of uncertainty in measurement (GUM:1995). – Geneva: ISO, 2008.

10.Montgomery D.C. Introduction to Statistical Quality Control. – 8th ed. – Hoboken: Wiley, 2019. – 768 p.

11.LeCun Y., Bengio Y., Hinton G. Deep learning // Nature. – 2015. – Vol. 521. – P. 436–444.

12.Tukhtasinov R., Kholmatova M. Smart monitoring of knitting machines in Uzbekistan industry // Uzbek Textile Journal. – 2023. – No. 2. – P. 19–28.

Downloads

Published

2026-05-31