摘要
可调谐二极管激光吸收光谱(TDLAS)层析成像是一种重要的光学非侵入式燃烧检测技术,能够实现燃烧场重要流场参数的成像测量。为解决现有TDLAS温度分布层析成像算法重建图像的空间分辨率与成像速度之间的矛盾,将多分辨率空间离散模型与多分辨率温度分布重建思想引入TDLAS层析成像,并以两级空间分辨率为例,具体构建基于双域多尺度特征融合的多分辨率温度层析成像网络(DMFMMnet)。该网络基于测量值域多尺度融合卷积,以较低的空间分辨率实现燃烧场温度分布主要特征与总体轮廓的快速重建;结合图像域自适应多尺度特征融合与测量值校正,实现燃烧场温度分布细节特征的精细重建。采用火焰动力学模拟器生成的仿真数据与TDLAS传感器获得的真实测量数据进行的重建实验表明,DMFMMnet能够以一个网络重建出两种具有不同空间分辨率的温度分布图像。在信噪比为30 dB~45 dB的范围内,与需要在每个空间分辨率下调整结构并重新训练的现有温度重建网络相比,DMFMMnet重建的低分辨率、高分辨率温度分布图像的峰值信噪比分别提升了1.98%~32.79%和0.29%~38.67%。
Objective Tunable diode laser absorption spectroscopy(TDLAS)tomography is an important optical non-invasive combustiondetection technique that enables the imaging of critical flow-field parameters in the combustion field.The existing network-based TDLAS temperature tomographic algorithms are typically constructed with a fixed spatial resolution.If the target resolution is changed,then the network structure should be adjusted and the network retrained accordingly.Images reconstructed by these separate networks do not present a clear spatial correspondence,which renders it inconvenient to combine features in images with different spatial resolutions for combustion diagnosis.Hence,multiresolution spatial discretization modeling and multiresolution temperaturedistribution reconstruction were introduced into TDLAS tomography.Based on reconstruction at two spatial resolutions as an example,a dual-domain multiscale feature-based multiresolution temperature tomographic network(DMFMMnet)was constructed.Methods The proposed DMFMMnet extracts and adaptively merges multiscale spatial features in the TDLAS measurement and image domains to reconstruct low-resolution and high-resolution temperature images with spatial correspondence.First,it extracts multiscale spatial correlation features from TDLAS measurements and reconstructs the overall profile of the temperature distribution rapidly at a low resolution using a low-resolution reconstruction block(LBlock).Second,it performs multiscale feature extraction and adaptive feature merging on the reconstructed low-resolution temperature image using an image-domain multiscale feature extraction and merging block(IMBlock).Third,it combines multiscale spatial features extracted in the TDLAS measurement and image domains to reconstruct a high-resolution temperature image,which presents detailed features of the temperature distribution via feature enhancement and a high-resolution reconstruction block(HBlock).Results and Discussions To examine the performance of the proposed DMFMMnet,it was compared with two existing networkbased temperature tomographic algorithms.One is based on a convolutional neural network(H-CNN)and the other is based on a hierarchical vision Transformer and multiscale feature merging(HVTMFnet).These two networks were adjusted and trained for lowresolution reconstruction(with suffix-LR)and high-resolution reconstruction(with suffix-HR),separately.Furthermore,to examine the super-resolution reconstruction performance of IMBlock and HBlock in DMFMMnet,they were compared with the classical bicubic linear interpolation(bicubic)and two super-resolution networks,i.e.,super-resolution using deep convolutional networks(SRCNNs)and Transformer for single-image super-resolution(ESRT).The resulting high-resolution reconstruction networks combined with LBlock are referred to as LBlock+Bicubic,LBlock+SRCNN,and LBlock+ESRT.In the simulations,the dataset was generated using a fire dynamics simulator(FDS).Tests were performed in the signal-to-noise ratio(SNR)range of 25 dB‒45 dB.The peak signal-to-noise ratio(PSNR)and structural similarity(SSIM)were used to measure the reconstruction quality.The simulation results show that,for low-resolution reconstruction,the average PSNR values obtained by DMFMMnet are higher than those obtained by H-CNN-LR and HVTMFnet-LR at any SNR(Table 2).For high-resolution reconstruction,the average PSNR values obtained by DMFMMnet are higher than those obtained by H-CNN-HR,HVTMFnet-HR,LBlock+Bicubic,LBlock+SRCNN,and LBlock+ESRT in the SNR range of 30 dB‒45 dB(Table 3).In terms of subjective quality,the lowresolution temperature image reconstructed by DMFMMnet reflects the overall contour of the temperature distribution more clearly than those reconstructed by H-CNN-LR and HVTMFnet-LR(Fig.7),whereas the high-resolution temperature image reconstructed by DMFMMnet shows more accurate and detailed information than those reconstructed by H-CNN-HR,HVTMFnet-HR,LBlock+Bicubic,LBlock+SRCNN,and LBlock+ESRT(Fig.8).In the multiresolution temperature reconstruction experiments based on actual TDLAS measurements,the flame contour in the low-resolution temperature image reconstructed by DMFMMnet is more consistent with that of an annular burner,as compared with those reconstructed by H-CNN-LR and HVTMFnet-LR.The highresolution temperature image reconstructed by DMFMMnet shows more explicit thermal-diffusion characteristics in the combustion field than those reconstructed by H-CNN-HR,HVTMFnet-HR,LBlock+Bicubic,LBlock+SRCNN,and LBlock+ESRT(Fig.9).Additionally,compared with the peak temperature values retrieved by the other algorithms,the peak temperature values retrieved by DMFMMnet are more similar to the highest temperature values measured by the thermocouples.Conclusions Multiresolution spatial discretization modeling and multiresolution temperature reconstruction were introduced into TDLAS tomography. A multiresolution temperature tomography network (DMFMMnet) based on dual-domain multiscale featuremerging was constructed. This network reconstructs temperature images at two spatial resolutions with different computing costs,which can balance between imaging time and resolution. The simulation results show that the average PSNR values of the lowresolutiontemperature images reconstructed by DMFMMnet are 24.95%‒32.79% and 0.66%‒3.28% higher than those reconstructedby H-CNN-LR and HVTMFnet-LR, respectively, in the SNR range of 25 dB ‒ 40 dB. The average PSNR values of the highresolutiontemperature images reconstructed by DMFMMnet are 32.63%‒38.67%, 2.34%‒6.18%, 3.18%‒9.24%, 3.22%‒6.48%,and 0.29% ‒ 1.18% higher than those reconstructed by H-CNN-HR, HVTMFnet-HR, LBlock+Bicubic, LBlock+SRCNN, andLBlock+ESRT, respectively, in the SNR range of 30 dB‒45 dB. The flame contours in the low-resolution temperature images andthe detailed features in the high-resolution temperature images reconstructed by DMFMMnet are more similar to the ground-truthphantoms, as compared with the algorithms investigated. Experiments based on actual measurements obtained from the TDLASsensor show that the temperature images reconstructed by DMFMMnet can more accurately reflect the actual heat conduction in thecombustion field, as compared with the algorithms investigated.
作者
司菁菁
王静波
程银波
刘畅
Si Jingjing;Wang Jingbo;Cheng Yinbo;Liu Chang(School of Information Science and Engineering,Yanshan University,Qinhuangdao 066004,Hebei,China;Ocean College,Hebei Agricultural University,Qinhuangdao 066003,Hebei,China;School of Engineering,the University of Edinburgh,Edinburgh EH93JL,UK;Hebei Key Laboratory of Information Transmission and Signal Processing,Qinhuangdao 066004,Hebei,China)
出处
《中国激光》
CSCD
北大核心
2024年第23期124-136,共13页
Chinese Journal of Lasers
基金
国家自然科学基金(62371415)
河北省自然科学基金(F2021203027)
河北省重点实验室项目(202250701010046)
燕山大学基础创新科研培育项目(2021LGZD011)。
关键词
可调谐二极管激光吸收光谱
多分辨率层析成像
温度成像
多尺度特征融合
tunable diode laser absorption spectroscopy
multi-resolution tomography
temperature imaging
multi-scale feature merging
