Simultaneous measurement of temperature and pressure using deep-learning-assisted femtosecond laser-induced scattering technique
Authors:
- Jingwei ChenJCJingwei Chen
- Linhui ChenLCLinhui Chen
- Zhentian HaoZHZhentian Hao
- Jijin WangJWJijin Wang
- Shaohua SunSSShaohua Sun
- Zuoye LiuZLZuoye Liu
- Bitao HuBHBitao Hu
- Pengji DingPDPengji Ding
- 28 May 2025
- journal article
- Published by Optica Publishing Group in Optics Express
- Vol. 33 (11) , 23740-23754
Abstract
Femtosecond laser-induced grating scattering (fs-LIGS) technique has emerged as a robust diagnostic technique for combustion flow field characterization, particularly in temperature and pressure measurements. This study investigates four deep learning architectures for the simultaneous prediction of gas-phase temperature and pressure from raw fs-LIGS signals, including fully connected neural networks (FCNN), convolutional neural networks (CNN), bidirectional long short-term memory networks (BiLSTM), and a hybrid CNN-BiLSTM model. All architectures demonstrated exceptional predictive accuracy, achieving mean percentage errors ranging from −3.94% to 0.32% for temperature estimation and −0.26% to 1.09% for pressure estimation. The detailed comparison of the four models suggests that the LSTM structures have better adaptability for the measurements of temperature and pressure. In contrast the, CNN-BiLSTM model demonstrated superior overall performance in terms of predictive accuracy, cross-validation robustness, convergence rate, memory requirements, etc. Successful integration of these deep learning approaches with an fs-LIGS system would establish a novel framework for real-time, multi-parameter combustion diagnostics.Keywords
Funding Information
- National Natural Science Foundation of China (12004147, 12305166, 12034013)
- National Key Research and Development Program of China (2022YFE0103900)
- Open project of Shanghai Institute of Optics and Fine Mechanics
- Basic and Applied Basic Research Foundation of Guangdong Province (2022A1515140179)
This publication has 40 references indexed in Scilit:
- Intelligent controllable ultrafast fiber laser via deep learning and adaptive optimization algorithmInfrared Physics & Technology, 2024
- Determination of La in rare earth ores using laser-induced breakdown spectroscopy combined with bidirectional long short-term memoryApplied Physics B, 2024
- Research on particle swarm optimization in LSTM neural networks for rainfall-runoff simulationJournal of Hydrology, 2022
- Review on Convolutional Neural Networks (CNN) in vegetation remote sensingISPRS Journal of Photogrammetry and Remote Sensing, 2021
- An LSTM-based aggregated model for air pollution forecastingAtmospheric Pollution Research, 2020
- CNNpred: CNN-based stock market prediction using a diverse set of variablesExpert Systems with Applications, 2019
- Pressure measurement in combusting and non-combusting gases using laser-induced grating spectroscopyApplied Physics B, 2019
- High precision in-cylinder gas thermometry using Laser Induced Gratings: Quantitative measurement of evaporative cooling with gasoline/alcohol blends in a GDI optical engineCombustion and Flame, 2014
- Local fuel concentration measurements for mixture formation diagnostics using diffraction by laser‐induced gratings in comparison to spontaneous Raman scatteringJournal of Raman Spectroscopy, 2008
- Thermal grating and broadband degenerate four-wave mixing spectroscopy of OH in high-pressure flamesApplied Physics B, 1998