Guoliang Li

Guoliang Li

Auto-generated profile, based on publicly available information

Guoliang Li

School of Information Science and Engineering, Yanshan University, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 September 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
JSJingjing Si
Jingjing Si
GLGuoliang Li
Guoliang Li
YCYinbo Cheng
Yinbo Cheng
RZRui Zhang
Rui Zhang
EGEnemali Godwin
Enemali Godwin
CLChang Liu
Chang Liu
As an in situ combustion diagnostic tool, tunable diode laser absorption spectroscopy (TDLAS) tomography has been widely used for imaging 2-D temperature distributions in reactive flows. Compared with the computational tomographic algorithms, convolutional neural networks (CNNs) have been proved to be more robust and accurate for image reconstruction, particularly in the case of limited access of laser beams in the region of interest (RoI). In practice, the flame in the RoI that requires to be reconstructed with the good spatial resolution is commonly surrounded by low-temperature background. Although the background is not of high interest, spectroscopic absorption still exists due to heat dissipation and gas convection. Therefore, we propose a pseudoinversed CNN (PI-CNN) for hierarchical temperature imaging that: 1) uses efficiently the training and learning resources for temperature imaging in the RoI with good spatial resolution and 2) reconstructs the less spatially resolved background temperature by adequately addressing the integrity of the spectroscopic absorption model. In comparison with the traditional CNN, the newly introduced pseudoinversion of the RoI sensitivity matrix is more penetrating for revealing the inherent correlation between the projection data and the RoI to be reconstructed, thus prioritizing the temperature imaging in the RoI with high accuracy and high computational efficiency. In this article, the proposed algorithm was validated by both numerical simulation and lab-scale experiment, indicating good agreement between the phantoms and the high-fidelity reconstructions.

19 May 2023
Verified
Conference Paper
Open access
JSJingjing Si
Jingjing Si
DLDongcan Lv
Dongcan Lv
GLGuoliang Li
Guoliang Li
YCYinbo Cheng
Yinbo Cheng
Tunable Diode Laser Absorption Spectroscopy (TDLAS) tomography is a well-accepted non-contact combustion diagnosis technique by imaging two-dimensional (2-D) cross-sectional distribution of flow parameters in the combustion field. With the boom of applying learning-based algorithms for solving underdetermined inverse problem, some data-driven tomographic schemes have been developed for TDLAS tomography. In this work, a Multi-Layer Perceptron based TDLAS temperature imaging Network (MLP-Net) is established for the reconstruction of 2-D temperature distribution in the entire sensing region from limited projection data. With simulations, the reconstruction performance of MLP-Net is compared quantitatively and visually to the Extreme Learning Machine based Temperature imaging algorithm (ELM-T) and the Convolutional Neural Network based Temperature imaging algorithm (CNN-T). Simulation results show that MLP-Net can achieve higher reconstruction performance than ELM-T and CNN-T.