A Quality-Hierarchical Temperature Imaging Network for TDLAS Tomography

Si, Jingjing; Fu, Gengchen; Cheng, Yinbo; Zhang, Rui; Enemali, Godwin; Liu, Chang

doi:10.1109/tim.2022.3144211

Cited by 14 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gaussian flames were utilized to simulate real flames, and a stochastic mixed Gaussian flame model was constructed to generate Gaussian flames with varying numbers of peaks and peaks with stochasticity [31,32]. This approach enables the simulation of complex temperature distributions in actual combustion fields.…”

Section: Dataset Preparationmentioning

confidence: 99%

Multi-View Synthesis of Sparse Projection of Absorption Spectra Based on Joint GRU and U-Net

Shi,

Hao,

Huang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Tunable diode laser absorption spectroscopy (TDLAS) technology, combined with chromatographic imaging algorithms, is commonly used for two-dimensional temperature and concentration measurements in combustion fields. However, obtaining critical temperature information from limited detection data is a challenging task in practical engineering applications due to the difficulty of deploying sufficient detection equipment and the lack of sufficient data to invert temperature and other distributions in the combustion field. Therefore, we propose a sparse projection multi-view synthesis model based on U-Net that incorporates the sequence learning properties of gated recurrent unit (GRU) and the generalization ability of residual networks, called GMResUNet. The datasets used for training all contain projection data with different degrees of sparsity. This study shows that the synthesized full projection data had an average relative error of 0.35%, a PSNR of 40.726, and a SSIM of 0.997 at a projection angle of 4. At projection angles of 2, 8, and 16, the average relative errors of the synthesized full projection data were 0.96%, 0.19%, and 0.18%, respectively. The temperature field reconstruction was performed separately for sparse and synthetic projections, showing that the application of the model can significantly improve the reconstruction accuracy of the temperature field of high-energy combustion.

show abstract

Section: Dataset Preparationmentioning

confidence: 99%

Multi-View Synthesis of Sparse Projection of Absorption Spectra Based on Joint GRU and U-Net

Shi,

Hao,

Huang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The output reconstructed coarse-quality images provide faster temperature reconstruction, which can meet the requirement for real-time active monitoring of turbulent-chemical interactions. The fine-quality images can be lay in offline and used for analysis and diagnosis to further refine temperature reconstruction [37]. The research group also proposed a pseudoinversed convolutional neural network (PI-CNN) algorithm for hierarchical temperature imaging, and the numerical simulation and experimental verification were in good consistency [38].…”

Section: Gas Detectionmentioning

confidence: 99%

Application and algorithm research of TDLAS

Lao

Chen

Zhongkai

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Tunable diode laser absorption spectroscopy (TDLAS) is extensively utilized in monitoring of trace gases in the environment. With the relative entropy tomographic reconstruction, simultaneous multiplicative algebraic reconstruction technique algorithm and optimization of existing functions and models, TDLAS has been applied to reconstruction of temperature and humidity field, combustion diagnosis, mass flow monitoring and other domains, this paper will analyze the existing TDLAS application and algorithm research.

show abstract

“…Short-term Memory (LSTM) based tomographic algorithm [18], and a Swin Transformer based tomographic algorithm [19] were demonstrated on more practical TDLAST sensors with a small number of laser beams. However, all these data-driven methods are only capable of reconstructing the predetermined Region of Interest (RoI) with fixed resolution.…”

Section: Introductionmentioning

confidence: 99%

A Spatially Progressive Neural Network for Locally/Globally Prioritized TDLAS Tomography

Liu

et al. 2023

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

Tunable diode laser absorption spectroscopy tomography (TDLAST) has been widely applied for imaging two-dimensional distributions of industrial flow-field parameters, e.g., temperature and species concentration. Two main interested imaging objectives in TDLAST are the local combustion and its radiation in the entire sensing region. State-of-the-art algorithms were developed to retrieve either of the two objectives. In this paper, we address the both by developing a novel multi-output imaging neural network, named as Spatially Progressive Neural Network (SpaProNet). This network consists of locally and globally prioritized reconstruction stages. The former enables hierarchical imaging of the finely resolved and highly accurate local combustion, but coarsely resolved background. The later retrieves a fine-resolved image for the entire sensing region, at the cost of slightly trading off the reconstruction accuracy in the combustion zone. Furthermore, the proposed network is driven by the hydrodynamics of the real reactive flows, in which the training dataset is obtained from large eddy simulation. The proposed SpaProNet is validated by both simulation and lab-scale experiment. In all test cases, the visual and quantitative metric comparisons show that the proposed SpaProNet outperforms the existing methods from the following two perspectives: a) the locally prioritized stage provides ever-better accuracy in the combustion zone; b) the globally prioritized stage shows turbulence-indicative accuracy in the entire sensing region for diagnosis of heat radiation from the flame and flame-air interactions.

show abstract

A Quality-Hierarchical Temperature Imaging Network for TDLAS Tomography

Cited by 14 publications

References 36 publications

Multi-View Synthesis of Sparse Projection of Absorption Spectra Based on Joint GRU and U-Net

Multi-View Synthesis of Sparse Projection of Absorption Spectra Based on Joint GRU and U-Net

Application and algorithm research of TDLAS

A Spatially Progressive Neural Network for Locally/Globally Prioritized TDLAS Tomography

Contact Info

Product

Resources

About