A quality-hierarchical temperature imaging network for TDLAS tomography

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

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)
6 Downloads (Pure)


Tunable diode laser absorption spectroscopy (TDLAS) tomography is a well-established combustion diagnostic technique for imaging 2-D cross-sectional distributions of critical flow-field parameters. As two key metrics in TDLAS tomography, reconstruction accuracy and efficiency are generally traded off to satisfy either the requirement of high-fidelity image retrieval or rapid tomographic data inversion. In this article, a novel quality-hierarchical temperature imaging network for TDLAS tomography is developed based on stacked long short-term memory (LSTM). From limited line-of-sight TDLAS measurements, this network outputs two reconstructed temperature images, i.e., a coarse-quality image and a fine-quality image, with different numbers of network layers and consequently different computational costs. The coarse-quality image provides more timely temperature reconstruction, which can satisfy real-time dynamic monitoring of turbulence–chemistry interactions with a temporal resolution of tens of kilo frames per second. In contrast, the fine-quality image, which can be stored and utilized for offline analysis and diagnosis, further details the temperature reconstruction with more accurate features. Both numerical stimulation and lab-scale experiment validated the accuracy-efficiency tradeoff achieved by the proposed quality-hierarchical temperature imaging network.
Original languageEnglish
Article number4500710
JournalIEEE Transactions on Instrumentation and Measurement
Publication statusPublished - 18 Jan 2022


  • tomography
  • temperature measurement
  • laser beams
  • image reconstruction
  • measurement by laser beam
  • temperature sensors
  • temperature distribution


Dive into the research topics of 'A quality-hierarchical temperature imaging network for TDLAS tomography'. Together they form a unique fingerprint.

Cite this