Abstract. This paper investigates the accuracy and reliability of metrological systems used for industrial process measurements in the context of digital transformation. The study addresses the scientific challenge arising from the increasing complexity of modern production environments, where conventional metrological methods often fail to provide the required level of measurement accuracy. To overcome this limitation, an adaptive metrological approach integrating IoT-based sensor networks, real-time calibration procedures, and artificial intelligence-driven correction mechanisms is proposed. The proposed methodology enables continuous monitoring and dynamic adjustment of measurement parameters under changing operating conditions. The research findings demonstrate that the application of adaptive calibration algorithms improves measurement accuracy by 23%, while the integration of IoT-enabled sensor networks reduces the measurement error margin to ±0.02%. These results provide significantly higher reliability and lower uncertainty compared to traditional measurement techniques. The scientific novelty of the study lies in the development of a multilayer metrological system integrated with artificial intelligence modules capable of adapting to dynamic industrial environments and maintaining stable performance under both standard and extreme operating conditions. The proposed approach has considerable practical potential for quality control systems in the oil and gas, mechanical engineering, and pharmaceutical industries, and may also contribute to the modernization of national metrological standards.

Keywords: metrology, measurement accuracy, calibration, digital transformation, IoT sensors, uncertainty analysis, industrial measurement, smart sensors, traceability, quality control

DOWNLOAD ARTICLE

View