Bilson, S; Thompson, A; Tucker, D; Pearce, J (2023) A machine learning approach to automation and uncertainty evaluation for self-validating thermocouples. NIST Special Publication, 2100 (05). p. 85.

Full text not available from this repository.

Abstract

Thermocouples are in widespread use in industry, but they are particularly susceptible to calibration drift in harsh environments. Self-validating thermocouples, developed by NPL in collaboration with UK thermocouple manufacturer CCPI Europe, and being commercialized under the trade name INSEVA, aim to address this issue by using a miniature phase-change cell (fixed-point) in close proximity to the measurement junction (tip) of the thermocouple. The fixed point is a crucible containing an ingot of metal with a known melting temperature. When the process temperature being monitored passes through the melting temperature of the ingot, the thermocouple output exhibits a `plateau' during melting. Since the melting temperature of the ingot is known, the thermocouple can be recalibrated in-situ.

The main outstanding problem now is to automate the identification of the melting plateau. Quantifying the melting plateau to determine the onset of melting is reasonably well established, but requires manual intervention using techniques of zooming in on the region around the actual melting temperature, a process which can depend on the shape of the melting curve.

For the first time, we present a novel machine learning approach to recognise and identify the characteristic shape of the melting curve and, once identified, to quantity the point at which melting begins, along with its associated uncertainty. This removes the need for human intervention in locating and characterizing the melting point. Results from test data provided by CCPI Europe show 99% accuracy of melting plateau detection. They also show a cross-validated R^2 of 0.99 on predictions of calibration drift.

Item Type:	Article
Subjects:	Mathematics and Scientific Computing > Numerical Computation
Divisions:	Data Science
Identification number/DOI:	10.6028/NIST.SP.2100-05
Last Modified:	06 Jul 2023 11:08
URI:	https://eprintspublications.npl.co.uk/id/eprint/9785