Modern measuring instruments regulated by legal requirements such as in Legal Metrology are subject to conformity assessment and require a certification to ensure the compliance of instruments during use. However, such conformity assessment is usually version specific and a continuous monitoring or functional identification of these instruments during use could potentially replace repetitive conformity assessments and reverifications in the field. In this paper, we develop an extension to a state-of-the-art deep machine learning framework to interpret and analyze system logbooks describing the time-dependent behavior of regulated measuring instruments, realizing continuous quality control of such instruments via continually monitoring and identifying the instruments’ behavior. We also evaluate the performance and investigate the advantages of the approach. It is envisioned that the approach could be added as an acceptable solution to legal regulations and could facilitate fully automatic quality control of modern measuring instruments.
Themenbereich der Metrologie
Mathematik und metrologische Informationstechnik
Innovationscluster
Digitalisierung
; Systemische Metrologie
Geschäftsfelder
Metrologie für die Gesellschaft
; Metrologie für die Wirtschaft
Zitierung
Ho, L. C. X., Esche, M., Nischwitz, M., Glesner, S., & Maue, M. (2025). Deep machine learning for identifying time-series functions of regulated measuring instruments. 2025 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Chemnitz, 19-22, Mai, 2025, Deutschland. https://doi.org/10.1109/I2MTC62753.2025.11079053
