Skip to main content
SpringerLink
Log in

Efficient and robust CNN-LSTM prediction of flame temperature aided light field online tomography

  • Article
  • Published:
Science China Technological Sciences Aims and scope Submit manuscript

Abstract

Light field tomography, an optical combustion diagnostic technology, has recently attracted extensive attention due to its easy implementation and non-intrusion. However, the conventional iterative methods are high data throughput, low efficiency and time-consuming, and the existing machine learning models use the radiation spectrum information of the flame to realize the parameter field measurement at the current time. It is still an offline measurement and cannot realize the online prediction of the instantaneous structure of the actual turbulent combustion field. In this work, a novel online prediction model of flame temperature instantaneous structure based on deep convolutional neural network and long short-term memory (CNN-LSTM) is proposed. The method uses the characteristics of local perception, shared weight, and pooling of CNN to extract the three-dimensional (3D) features of flame temperature and outgoing radiation images. Moreover, the LSTM is used to comprehensively utilize the ten historical time series information of high dynamic combustion flame to accurately predict 3D temperature at three future moments. A chaotic time-series dataset based on the flame radiation forward model is built to train and validate the performance of the proposed CNN-LSTM model. It is proven that the CNN-LSTM prediction model can successfully learn the evolution pattern of combustion flame and make accurate predictions.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

References

  1. Ma L, Ning H, Wu J, et al. Characterization of temperature and soot volume fraction in laminar premixed flames: Laser absorption/extinction measurement and two-dimensional computational fluid dynamics modeling. Energy Fuels, 2018, 32: 12962–12970

    Article  Google Scholar 

  2. Alviso D, Mendieta M, Molina J, et al. Flame imaging reconstruction method using high resolution spectral data of OH*, CH* and C2* radicals. Int J Thermal Sci, 2017, 121: 228–236

    Article  Google Scholar 

  3. Goldenstein C S, Spearrin R M, Jeffries J B, et al. Infrared laser-absorption sensing for combustion gases. Prog Energy Combust Sci, 2017, 60: 132–176

    Article  Google Scholar 

  4. Shi J W, Qi H, Yu Z Q, et al. Three-dimensional temperature reconstruction of diffusion flame from the light-field convolution imaging by the focused plenoptic camera. Sci China Tech Sci, 2022, 65: 302–323

    Article  Google Scholar 

  5. Wang Q, Liu H C, Cai W W. Development of a single-camera volumetric thermometry for gas flows based on space division multiplexing. Sci China Tech Sci, 2022, 65: 1646–1650

    Article  Google Scholar 

  6. Liu Y, Zhu J, Liu G, et al. Assessment of various full-spectrum correlated K-distribution methods in radiative heat transfer in oxy-fuel sooting flames. Int J Thermal Sci, 2023, 184: 107919

    Article  Google Scholar 

  7. Zhang Z, Lou C, Long Y, et al. Thermodynamics second-law analysis of hydrocarbon diffusion flames: Effects of soot and temperature. Combust Flame, 2021, 234: 111618

    Article  Google Scholar 

  8. Ouyang Z X, Yang H, Lu J, et al. Real-time adaptive particle image velocimetry for accurate unsteady flow field measurements. Sci China Tech Sci, 2022, 65: 2143–2155

    Article  Google Scholar 

  9. Li T J, Yuan Y, Shuai Y, et al. Joint method for reconstructing three-dimensional temperature of flame using Lucy-Richardson and nearest neighbor filtering using light-field imaging. Sci China Tech Sci, 2019, 62: 1232–1243

    Article  Google Scholar 

  10. Grauer S J, Unterberger A, Rittler A, et al. Instantaneous 3D flame imaging by background-oriented schlieren tomography. Combust Flame, 2018, 196: 284–299

    Article  Google Scholar 

  11. Zhang J, Qi H, Ren Y, et al. Acoustic tomography of temperature and velocity fields by using the radial basis function and alternating direction method of multipliers. Int J Heat Mass Transfer, 2022, 188: 122660

    Article  Google Scholar 

  12. Ma X, Xu H, Jiang C, et al. Ultra-high speed imaging and OH-LIF study of DMF and MF combustion in a DISI optical engine. Appl Energy, 2014, 122: 247–260

    Article  Google Scholar 

  13. Shui C, Huang J, Liu H, et al. Tomographic absorption spectroscopy based on dictionary learning. Opt Express, 2021, 29: 36400

    Article  Google Scholar 

  14. Tancin R J, Spearrin R M, Goldenstein C S. 2D mid-infrared laserabsorption imaging for tomographic reconstruction of temperature and carbon monoxide in laminar flames. Opt Express, 2019, 27: 14184–14198

    Article  Google Scholar 

  15. Huang J, Li S, Cai W, et al. Quantification of the size, 3D location and velocity of burning iron particles in premixed methane flames using high-speed digital in-line holography. Combust Flame, 2021, 230: 111430

    Article  Google Scholar 

  16. Gilabert G, Lu G, Yan Y. Three-dimensional tomographic reconstruction of the luminosity distribution of a combustion flame. IEEE Trans Instrum Meas, 2007, 56: 1300–1306

    Article  Google Scholar 

  17. Liu Y, Zhu M, Wang T, et al. Spatial resolution of light field sectioning pyrometry for flame temperature measurement. Optics Lasers Eng, 2021, 140: 106545

    Article  Google Scholar 

  18. Tan Z P, Johnson K, Clifford C, et al. Development of a modular, high-speed plenoptic-camera for 3D flow-measurement. Opt Express, 2019, 27: 13400

    Article  Google Scholar 

  19. Niu Z T, Qi H, Shi J W, et al. Temperature field reconstruction of3D luminous flames based on light field tomography theory. Sci China Tech Sci, 2021, 64: 223–236

    Article  Google Scholar 

  20. Yan W, Lou C. Two-dimensional distributions of temperature and soot volume fraction inversed from visible flame images. Exp Thermal Fluid Sci, 2013, 50: 229–233

    Article  Google Scholar 

  21. Daun K J, Grauer S J, Hadwin P J. Chemical species tomography of turbulent flows: Discrete ill-posed and rank deficient problems and the use of prior information. J Quant Spectr Radiat Transfer, 2016, 172: 58–74

    Article  Google Scholar 

  22. Wang F, Wu Q, Huang Q, et al. Simultaneous measurement of 2-dimensional H2O concentration and temperature distribution in pre-mixed methane/air flame using TDLAS-based tomography technology. Optics Commun, 2015, 346: 53–63

    Article  Google Scholar 

  23. Liu D, Wang F, Cen K, et al. Noncontact temperature measurement by means of CCD cameras in a participating medium. Opt Lett, 2008, 33: 422

    Article  Google Scholar 

  24. Li T, Zhang C, Liu D. Simultaneously retrieving of soot temperature and volume fraction in participating media and laminar diffusion flame using multi-spectral light field imaging. Int J Thermal Sci, 2023, 193: 108472

    Article  Google Scholar 

  25. Liu D, Yan J, Wang F, et al. Experimental reconstructions of flame temperature distributions in laboratory-scale and large-scale pulverized-coal fired furnaces by inverse radiation analysis. Fuel, 2012, 93: 397–403

    Article  Google Scholar 

  26. Liu D, Wang F, Yan J H, et al. Inverse radiation problem of temperature field in three-dimensional rectangular enclosure containing inhomogeneous, anisotropically scattering media. Int J Heat Mass Transfer, 2008, 51: 3434–3441

    Article  Google Scholar 

  27. Li T J, Zhang C X, Yuan Y, et al. Effect of nonuniform radiation properties on flame temperature reconstruction based on light field imaging. Int Commun Heat Mass Transfer, 2019, 104: 136–146

    Article  Google Scholar 

  28. Wei C, Schwann K K, Pineda D I, et al. Volumetric laser absorption imaging of temperature, CO and CO2 in laminar flames using 3D masked Tikhonov regularization. Combust Flame, 2021, 224: 239–247

    Article  Google Scholar 

  29. Niu Z T, Qi H, Zhu Z Y, et al. A novel parametric level set method coupled with Tikhonov regularization for tomographic laser absorption reconstruction. Appl Thermal Eng, 2022, 201: 117819

    Article  Google Scholar 

  30. Ihme M, Chung W T, Mishra A A. Combustion machine learning: Principles, progress and prospects. Prog Energy Combust Sci, 2022, 91: 101010

    Article  Google Scholar 

  31. Lou S, Li D H W, Lam J C, et al. Prediction of diffuse solar irradiance using machine learning and multivariable regression. Appl Energy, 2016, 181: 367–374

    Article  Google Scholar 

  32. Wu H, Zhang H, Hu G, et al. Deep learning-based reconstruction of the structure of heterogeneous composites from their temperature fields. AIP Adv, 2020, 10: 045037

    Article  Google Scholar 

  33. Ren T, Li H, Modest M F, et al. Efficient two-dimensional scalar fields reconstruction of laminar flames from infrared hyperspectral measurements with a machine learning approach. J Quant Spectr Radiat Transfer, 2021, 271: 107724

    Article  Google Scholar 

  34. Si J, Li G, Cheng Y, et al. Hierarchical temperature imaging using pseudoinversed convolutional neural network aided tdlas tomography. IEEE Trans Instrum Meas, 2021, 70: 1–11

    Google Scholar 

  35. Wang Z, Song C, Chen T. Deep learning based monitoring of furnace combustion state and measurement of heat release rate. Energy, 2017, 131: 106–112

    Article  Google Scholar 

  36. Ren T, Modest M F, Fateev A, et al. Machine learning applied to retrieval of temperature and concentration distributions from infrared emission measurements. Appl Energy, 2019, 252: 113448

    Article  Google Scholar 

  37. Huang J, Liu H, Wang Q, et al. Limited-projection volumetric tomography for time-resolved turbulent combustion diagnostics via deep learning. Aerospace Sci Tech, 2020, 106: 106123

    Article  Google Scholar 

  38. Deng A, Huang J, Liu H, et al. Deep learning algorithms for temperature field reconstruction of nonlinear tomographic absorption spectroscopy. Measurement-Sens, 2020, 10–12: 100024

    Article  Google Scholar 

  39. Jin Y, Zhang W, Song Y, et al. Three-dimensional rapid flame chemiluminescence tomography via deep learning. Opt Express, 2019, 27: 27308–27334

    Article  Google Scholar 

  40. Niu Z T, Qi H, Shi J W, et al. Three-dimensional rapid visualization of flame temperature field via compression and noise reduction of light field imaging. Int Commun Heat Mass Transfer, 2022, 137: 106270

    Article  Google Scholar 

  41. Gao B H, Qi H, Zhao Y, et al. An efficient equation-solving method for calculating radiative transfer in isotropic scattering medium. Int J Heat Mass Transfer, 2021, 174: 121298

    Article  Google Scholar 

  42. Gao B H, Qi H, Yin Y M, et al. Fast reconstructing two-dimensional temperature distribution in participating media with different surfaces conditions. Infrared Phys Tech, 2019, 103: 103080

    Article  Google Scholar 

  43. Si J, Fu G, Cheng Y, et al. A quality-hierarchical temperature imaging network for TDLAS tomography. IEEE Trans Instrum Meas, 2022, 71: 1–10

    Google Scholar 

  44. Fischer T, Krauss C. Deep learning with long short-term memory networks for financial market predictions. Eur J Oper Res, 2018, 270: 654–669

    Article  MathSciNet  Google Scholar 

  45. Lorenz E N. Deterministic nonperiodic flow. J Atmos Sci, 1963, 20: 130–141

    Article  MathSciNet  Google Scholar 

  46. Niu Z, Qi H, Gao B, et al. Three-dimensional inhomogeneous temperature tomography of confined-space flame coupled with wall radiation effect by instantaneous light field. Int J Heat Mass Transfer, 2023, 211: 124282

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Energy Science and Engineering, Harbin Institute of Technology, Harbin, 150001, China

    ZhiTian Niu, Hong Qi, AnTai Sun, YaTao Ren, MingJian He & BaoHai Gao

  2. Key Laboratory of Aerospace Thermophysics, Ministry of Industry and Information Technology, Harbin, 150001, China

    ZhiTian Niu, Hong Qi, AnTai Sun, YaTao Ren, MingJian He & BaoHai Gao

Authors
  1. ZhiTian Niu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hong Qi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. AnTai Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. YaTao Ren
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. MingJian He
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. BaoHai Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hong Qi.

Additional information

This work was supported by the National Natural Science Foundation of China (Grant No. 51976044, and 52227813) and the Foundation for Heilongjiang Touyan Innovation Team Program.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Niu, Z., Qi, H., Sun, A. et al. Efficient and robust CNN-LSTM prediction of flame temperature aided light field online tomography. Sci. China Technol. Sci. 67, 271–284 (2024). https://doi.org/10.1007/s11431-023-2466-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11431-023-2466-7

Search

Navigation