Improving the reliability of industrial reactors by using differential neural network architecture in ultrasonic tomography
Artykuł w czasopiśmie
MNiSW
5
spoza listy
| Status: | |
| Autorzy: | Rymarczyk Tomasz, Kulisz Monika, Kłosowski Grzegorz, Wójcik Dariusz, Kowalski Marcin, Król Krzysztof |
| Dyscypliny: | |
| Aby zobaczyć szczegóły należy się zalogować. | |
| Rok wydania: | 2026 |
| Wersja dokumentu: | Drukowana | Elektroniczna |
| Język: | angielski |
| Numer czasopisma: | 1 |
| Wolumen/Tom: | 28 |
| Strony: | 1 - 21 |
| Efekt badań statutowych | NIE |
| Finansowanie: | Publikacja sfinansowana przez współautorów. |
| Materiał konferencyjny: | NIE |
| Publikacja OA: | TAK |
| Licencja: | |
| Sposób udostępnienia: | Otwarte czasopismo |
| Wersja tekstu: | Ostateczna wersja opublikowana |
| Czas opublikowania: | W momencie opublikowania |
| Data opublikowania w OA: | 2 sierpnia 2025 |
| Abstrakty: | angielski |
| Ultrasonic tomography (UST) represents a powerful non-invasive diagnostic technique for monitoring and analyzing internal processes within industrial reactors. Despite its potential, UST-based reconstructions are often challenged by the ill-posed nature of the inverse problem, limited measurements, and the presence of noise. To address these limitations, this study introduces a novel differential neural network architecture that enhances conventional deep learning models by incorporating a specialized differential layer. This layer processes two parallel input streams and operates on their residuals, thereby amplifying subtle variations in the data critical for accurate tomographic reconstructions. This study aims to empirically validate the concept of the efficacy of differentiated architecture. Reconstruction performance was evaluated using established quantitative metrics. Results demonstrate that models incorporating the differential layer consistently outperform their standard counterparts, delivering higher resolution, improved structural integrity, and superior noise robustness. The universality and efficiency of the differential architecture across both sequential and spatial models highlight its applicability to a wide range of inverse imaging problems in industrial settings. |
