A novel method for error analysis in radiation thermometry with application to industrial furnaces

• Published in: Measurement : journal of the International Measurement Confederation Vol. 190; p. 110646
• Main Authors: Martinez, Iñigo, Otamendi, Urtzi, Olaizola, Igor G., Solsona, Roger, Maiza, Mikel, Viles, Elisabeth, Fernandez, Arturo, Arzua, Ignacio
• Format: Journal Article
• Language: English
• Published: London Elsevier Ltd 28.02.2022; Elsevier Science Ltd
• Subjects: Atmospheric models; Chemical industry; Continuous furnaces; Deep learning; Emissions; Error analysis; Error correction; Furnaces; Infrared imagery; Measurement; Monitoring; Monitoring system; Petrochemical industry; Petrochemicals; Radiation; Radiation thermometry; Real time operation; Surrogate model; Thermometers; Thermometry; Uncertainty; Monitoring system; Deep learning; Petrochemical industry; Radiation thermometry; Error analysis; Surrogate model; Infrared imagery
• ISSN: 0263-2241; 1873-412X
• DOI: 10.1016/j.measurement.2021.110646

Accurate temperature measurements are essential for the proper monitoring and control of industrial furnaces. However, measurement uncertainty is a risk for such a critical parameter. Certain instrumental and environmental errors must be considered when using spectral-band radiation thermometry techniques, such as the uncertainty in the emissivity of the target surface, reflected radiation from surrounding objects, or atmospheric absorption and emission, to name a few. Undesired contributions to measured radiation can be isolated using measurement models, also known as error-correction models. This paper presents a methodology for budgeting significant sources of error and uncertainty during temperature measurements in a petrochemical furnace scenario. A continuous monitoring system is also presented, aided by a deep-learning-based measurement correction model, to allow domain experts to analyze the furnace’s operation in real-time. To validate the proposed system’s functionality, a real-world application case in a petrochemical plant is presented. The proposed solution demonstrates the viability of precise industrial furnace monitoring, thereby increasing operational security and improving the efficiency of such energy-intensive systems. [Display omitted] •A methodology for budgeting major sources of error during radiation thermometry measurements.•Deep learning-based surrogate models are proposed for fast parameter inference.•An end-to-end computing architecture for thermal imagery acquisition & analysis.•Applied to a real-world application case in a petrochemical plant.