L. Milia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
L. Milia has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Alessandra Fanni
University of Cagliari
2 shared publications - Antonio Pimazzoni
Consorzio RFX (CNR, ENEA, INFN, Università di Padova, Acciaierie Venete SpA)
2 shared publications - Augusto Montisci
Department of Electrical and Electronic Engineering, University of Cagliari, 09123 Cagliari, Italy
2 shared publications - Barbara Cannas
University of Cagliari
2 shared publications - Enrico Aymerich
Department of Electrical and Electronic Engineering, University of Cagliari, 09123 Cagliari, Italy
2 shared publications - Fabio Pisano
University of Cagliari
2 shared publications
Latest Publications
- Open Access
- 2 July 2025
- Published by Elsevier in Fusion Engineering and Design
- Vol. 219
Automatic estimation of heat loads distribution on STRIKE through multi-layer perceptrons
- 2 July 2025
- Published by Elsevier in Fusion Engineering and Design
- Vol. 219
Open AccessAutomatic estimation of heat loads distribution on STRIKE through multi-layer perceptrons
- Open Access
- 23 June 2025
- Published by IOP Publishing in Plasma Physics and Controlled Fusion
- Vol. 67 (7) , 075007
Machine learning for solving the inverse thermal problem on STRIKE in real-time
The short time retractable instrumented calorimeter experiment is a critical diagnostic tool for characterizing the source for production of negative ions of deuterium extracted from radio frequency plasma. Due to technical limitations, direct temperature measurement on the calorimeter’s front side, facing the ion source, is infeasible. Instead, reconstructing the front-side heat flux from back-side temperature data formulates an inverse problem. This study introduces a convolutional neural network (CNN) to achieve real-time reconstruction of the heat flux distribution, modeled with Gaussian fitting for each beamlet, directly from infrared (IR) camera images. The CNN’s performance is benchmarked against a multi-layer perceptron (MLP) model, which requires offline parametrization of IR images, limiting real-time applicability. Using experimental IR images and heat flux data generated via iterative finite element method modelling, the CNN demonstrated comparable accuracy to the MLP without the need for feature extraction engineering, offering a robust real-time solution.
- 23 June 2025
- Published by IOP Publishing in Plasma Physics and Controlled Fusion
- Vol. 67 (7) , 075007
Open AccessMachine learning for solving the inverse thermal problem on STRIKE in real-time
The short time retractable instrumented calorimeter experiment is a critical diagnostic tool for characterizing the source for production of negative ions of deuterium extracted from radio frequency plasma. Due to technical limitations, direct temperature measurement on the calorimeter’s front side, facing the ion source, is infeasible. Instead, reconstructing the front-side heat flux from back-side temperature data formulates an inverse problem. This study introduces a convolutional neural network (CNN) to achieve real-time reconstruction of the heat flux distribution, modeled with Gaussian fitting for each beamlet, directly from infrared (IR) camera images. The CNN’s performance is benchmarked against a multi-layer perceptron (MLP) model, which requires offline parametrization of IR images, limiting real-time applicability. Using experimental IR images and heat flux data generated via iterative finite element method modelling, the CNN demonstrated comparable accuracy to the MLP without the need for feature extraction engineering, offering a robust real-time solution.