L.S. Zvyagin¹

¹Financial University under the Government of the Russian Federation (Moscow, Russia)

¹lszvyagin@fa.ru

The article considers the actual problem of metrological support of intelligent information and measurement systems. In the course of the research, the existing approaches to metrological support were analyzed, and their limitations were identified in relation to systems with elements of artificial intelligence. A conceptual model of the verification and validation process has been developed that integrates machine learning and deep learning algorithms to increase the reliability and accuracy of measurements. The practical implementation of the proposed methodology is described using the example of an algorithm for anomaly detection and self-diagnosis of intelligent information and measurement systems. Aim is to develop scientific and methodological foundations of metrological support for intelligent information and measurement systems based on the synergy of classical procedures for verification and validation of measurement data and modern artificial intelligence methods. The article proposes a comprehensive methodology based on the processes of verification and validation of measurement data using artificial intelligence methods.

The conducted research confirms that traditional metrological support methods are not sufficient for intelligent information and measurement systems, since they are not able to take into account the adaptability and dependence of results on training data. The proposed methodology, based on continuous verification and validation of measurement data using artificial intelligence methods, has proven to be highly effective. The results of experimental modeling using the autoencoder algorithm as an example show that intelligent methods are significantly superior to classical statistical approaches, especially in detecting complex, "creeping" anomalies such as zero drift and noise increase. The proposed conceptual model and the developed approaches lay the scientific and methodological foundation for creating reliable and reliable information and measurement systems, ensuring metrological traceability of not only the hardware, but also the intellectual component of the system, and also opens up new opportunities for integrating artificial intelligence into critical areas, increasing security and efficiency in the digital economy. and the concept of "Industry 4.0".

Zvyagin L.S. Metrological support of intelligent information and measurement systems based on data verification and validation using artificial intelligence methods. Information-measuring and Control Systems. 2026. V. 24. № 1. P. 23−33. DOI: https://doi.org/10.18127/j20700814-202601-03 (in Russian)

1. Acko B., Weber H., Hutzschenreuter D., Smith I. Communication and validation of metrological smart data in IoT‐networks. Advances in Production Engineering & Management. 2020; 15(1): 107-117. DOI: https://doi.org/10.14743/apem2020.1.353.
2. Grigorev V.V., Mityurev A.K., Pogonyshev A.O., Savkin K.B., Tikhomirov S.V. Metrologicheskoe obespechenie informatsionno-izmeritelnykh sistem na osnove volokonno-opticheskikh datchikov. Foton-ekspress. 2019; VKVO: 36−37. DOI: 10.24411/2308-6920-2019-16013. (in Russian)
3. Danilov A.A. Napravleniya sovershenstvovaniya izmeritelnykh sistem i ikh metrologicheskogo obespecheniya. Izmeritelnaya Tekhnika (Izmeritelʹnaya Tekhnika). 2023; (8): 24−29. DOI: https://doi.org/10.32446/0368-1025it.2023-8-24-29. (in Russian)
4. Selivanova Z.M., Skomorokhov K.V. Intellektualnaya informatsionno-izmeritelnaya sistema s rekonfiguriruemoi strukturoi dlya opredeleniya teploprovodnosti materialov. Priborostroenie. 2025; 68(8): 680-688. DOI: https://doi.org/10.17586/0021-3454-2025-68-8-680-688. (in Russian)
5. Barbosa C.R.H., et al. Smart Manufacturing and Digitalization of Metrology: A Systematic Literature Review and a Research Agenda. Sensors. 2022; 22(16): 6114. DOI: 10.3390/s22166114.
6. Eichstädt S., Keidel A., Tesch J. Metrology for the digital age. Measurement: Sensors. 2021; 18: 100232. DOI: 10.1016/j.measen. 2021. 100232.
7. Kucharski D. Machine Learning-Based Selection of Measurement Technique for Surface Metrology: A pilot study.
8. Obajemu O., et al. An interpretable machine learning based approach for process to areal surface metrology informatics. Surface Topography: Metrology and Properties. 2021; 9(4). DOI: 10.1088/2051-672X/ac28a7.
9. Peter H. Application of AI and Machine Learning in the Automated Metrological Verification of Precision Shunts.
10. Sobolev V., Aumala O. Metrological automatic support of measurement results in intelligent measurement systems. Measurement. 1996;17(3):151−159. DOI: 10.1016/0263-2241(96)00016-4.
11. Taymanov R., Sapozhnikova K. A New View on Metrological Maintenance of AI-based Systems. 2022 IEEE International Conference on Metrology for AeroSpace (MetroAeroSpace). XXXII International Scientific Symposium Metrology and Metrology Assurance (MMA). 07−11 September 2022. Sozopol, Bulgaria. 2022:1−6. DOI: 10.1109/MMA55579.2022.9992561.
12. Wieczorowski M., et al. A novel approach to using artificial intelligence in coordinate metrology including nano scale. Measurement. 2023; 217: 113051. DOI: 10.1016/j.measurement.2023.113051.
13. Zuo C., Qian J., Feng S., Yin W., Li Y., Fan P., Han J., Qian K., Chen Q. Deep learning in optical metrology: A review. Light: Science & Applications. 2022; 11(1): 39. DOI: 10.1038/s41377-022-00714-x.
14. Yu, Meng, Liu, Jianmin, Li, Xiaowen, Wang, Nana, Wang, Fan. Research on Intelligent Metrological Verification Technology Based on Internet of Things. Journal of Physics: Conference Series. 2021; 2108: 012058. DOI: 10.1088/1742-6596/2108/1/012058.
15. Zhu Y., Liu J. Design and Implementation of Intelligent Measurement Testing and Calibration Management Information System based on Big Data. Journal of Physics: Conference Series. IOP Publishing. 2019; 1237(4): 042038. DOI: 10.1088/1742-6596/1237/4/042038.