Temporal waveform denoising using deep learning for injection laser systems of inertial confinement fusion high-power laser facilities

Guardado en:
Detalles Bibliográficos
Publicado en:High Power Laser Science and Engineering vol. 12 (2025)
Autor principal: Chen, Wei
Otros Autores: Lu, Xinghua, Fan, Wei, Wang, Xiaochao
Publicado:
Cambridge University Press
Materias:
Acceso en línea:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 3151105667
003 UK-CbPIL
022 |a 2095-4719 
022 |a 2052-3289 
024 7 |a 10.1017/hpl.2024.60  |2 doi 
035 |a 3151105667 
045 2 |b d20250101  |b d20251231 
084 |a 254629  |2 nlm 
100 1 |a Chen, Wei  |u Key Laboratory of High Power Laser and Physics, Shanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Shanghai, China; Center of Materials Science and Optoelectronics Engineering, University of Chinese Academy of Sciences, Beijing, China 
245 1 |a Temporal waveform denoising using deep learning for injection laser systems of inertial confinement fusion high-power laser facilities 
260 |b Cambridge University Press  |c 2025 
513 |a Journal Article 
520 3 |a For the pulse shaping system of the SG-II-up facility, we propose a U-shaped convolutional neural network that integrates multi-scale feature extraction capabilities, an attention mechanism and long short-term memory units, which effectively facilitates real-time denoising of diverse shaping pulses. We train the model using simulated datasets and evaluate it on both the simulated and experimental temporal waveforms. During the evaluation of simulated waveforms, we achieve high-precision denoising, resulting in great performance for temporal waveforms with frequency modulation-to-amplitude modulation conversion (FM-to-AM) exceeding 50%, exceedingly high contrast of over 300:1 and multi-step structures. The errors are less than 1% for both root mean square error and contrast, and there is a remarkable improvement in the signal-to-noise ratio by over 50%. During the evaluation of experimental waveforms, the model can obtain different denoised waveforms with contrast greater than 200:1. The stability of the model is verified using temporal waveforms with identical pulse widths and contrast, ensuring that while achieving smooth temporal profiles, the intricate details of the signals are preserved. The results demonstrate that the denoising model, trained utilizing the simulation dataset, is capable of efficiently processing complex temporal waveforms in real-time for experiments and mitigating the influence of electronic noise and FM-to-AM on the time–power curve. 
653 |a Datasets 
653 |a Waveforms 
653 |a Deep learning 
653 |a Performance evaluation 
653 |a Wavelet transforms 
653 |a Injection lasers 
653 |a Lasers 
653 |a Artificial neural networks 
653 |a Noise reduction 
653 |a Neural networks 
653 |a High power lasers 
653 |a Algorithms 
653 |a Frequency modulation 
653 |a Machine learning 
653 |a Real time 
653 |a Efficiency 
653 |a Inertial confinement fusion 
653 |a Signal to noise ratio 
653 |a Amplitude modulation 
700 1 |a Lu, Xinghua  |u Key Laboratory of High Power Laser and Physics, Shanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Shanghai, China 
700 1 |a Fan, Wei  |u Key Laboratory of High Power Laser and Physics, Shanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Shanghai, China; Center of Materials Science and Optoelectronics Engineering, University of Chinese Academy of Sciences, Beijing, China 
700 1 |a Wang, Xiaochao  |u Key Laboratory of High Power Laser and Physics, Shanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Shanghai, China; Center of Materials Science and Optoelectronics Engineering, University of Chinese Academy of Sciences, Beijing, China 
773 0 |t High Power Laser Science and Engineering  |g vol. 12 (2025) 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3151105667/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3151105667/fulltext/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3151105667/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch