Diagnosing electron temperature using machine learning and neutral tungsten spectral emission. (March 2023)

• Record Type: Journal Article
• Authors: Johnson, C.A.; Unterberg, E.A.; Ennis, D.A.; Hartwell, G.J.; Maurer, D.A.
• Is Part Of: Nuclear materials and energy. Volume 34(2023)
• Publication Date: 2023-03
• Subjects: 00-01 -- 99-00; Spectroscopy -- Machine learning -- Line ratios -- Tungsten -- Collisional radiative; Nuclear energy -- Periodicals; Nuclear fuels -- Periodicals; Nuclear reactors -- Materials -- Periodicals; Radioactive substances -- Periodicals; 621.4833
• DOI: 10.1016/j.nme.2022.101304
• Languages: English
• ISSNs: 2352-1791

Abstract

Abstract: Current spectroscopic based erosion diagnostics require both T e and n e measurements in addition to detailed atomic physics and collisional radiative (CR) modeling. Machine Learning (ML) techniques are used to address the temperature measurement requirement for erosion diagnosis. ML techniques are combined with tungsten spectroscopic diagnosis trained with co-located Langmuir probe measurements in the Compact Toroidal Hybrid (CTH) to obtain a spectroscopic based local electron temperature diagnostic. Initial analysis using synthetic data and a Neutral Network (NN) suggests a temperature diagnostic obtained with experimental data is feasible. ML methods have the potential to bypass sources of error in traditional tungsten erosion diagnosis by taking the place of required atomic and CR modeling which introduce inherent uncertainties. Temperature diagnosed could be used as input to current erosion diagnosis techniques (the S/XB method). Highlights: Machine learning techniques are used to make local electron temperature measurements. UV neutral tungsten emission is used to obtain local electron temperature. Photon emissivity coefficients in the UV region for neutral tungsten are calculated.