Improved residual network based on attention mechanism for flame temperature field reconstruction

被引：0
作者：
Shan L. [1 ]
Zhou R. [1 ]
Hong B. [1 ]
Yang W. [1 ]
Kong M. [2 ]
机构：
[1] Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Zhejiang, Hangzhou
[2] College of Metrology and Measurement Engineering, China Jiliang University, Zhejiang, Hangzhou
来源：
Huagong Jinzhan/Chemical Industry and Engineering Progress | 2024年 / 43卷 / 02期
关键词：
attention mechanism; pooling; residual network; temperature field;
D O I：
10.16085/j.issn.1000-6613.2023-1354
中图分类号：
学科分类号：
摘要：
The method of reconstructing the flame temperature field based on convolutional neural network has been widely used in recent years, but the traditional convolutional neural network model is prone to overfitting or model degradation as the number of network layers increases, resulting in large reconstruction errors. This paper proposed an improved method, which used the ResNet18 network to reconstruct the flame temperature field, and introduced the attention mechanism and local importance pooling to optimize the extracted content, realized the full use of known information, and reduced the reconstruction error. The experimental results showed that after introducing the local importance pooling and attention mechanism at the same time, the average relative error of temperature field reconstruction was 0.13%, and the maximum relative error was 0.75%. Compared with the initial ResNet18 network, the average relative error was reduced by 31.58%. The maximum relative error was reduced by 34.21%. The influence of the two factors on the reconstruction accuracy was verified by ablation experiments. The results showed that the temperature field reconstruction accuracy after adding two improved modules at the same time was better than that after adding a single improved module, and the local importance pooling module had a significant effect on the accuracy improvement. © 2024 Chemical Industry Press Co., Ltd.. All rights reserved.
引用
收藏
页码：688 / 695
页数：7
相关论文
共 27 条
  • [1] WANG Zhining, YANG Xiehe, ZHANG Yang, Et al., I-/e-FGR effect on NO<sub>x</sub> emission of natural gas combustion, Chemical Industry and Engineering Progress, 38, 9, pp. 4327-4334, (2019)
  • [2] HAN Delin, LI Dan, WANG Tiantian, Et al., Emission characteristics of swirl premixed combustion stabilized using a displacing bluff body, Chemical Industry and Engineering Progress, 41, 6, pp. 2915-2923, (2022)
  • [3] LIU Yudong, Study of light field sectioning pyrometry for three-dimensional flame temperature measurement, (2020)
  • [4] YAN Huibo, TANG Guangtong, LI Lujiang, Et al., New progress of algorithm for three-dimensional temperature field in large scale furnace measured by thermal radiative imaging, Clean Coal Technology, 28, 5, pp. 97-108, (2022)
  • [5] SUN Jun, XU Chuanlong, ZHANG Biao, Et al., Three-dimensional temperature measurement of the flame using the light field camera with a multiple focus microlens array, Journal of Engineering Thermophysics, 38, 10, pp. 2164-2170, (2017)
  • [6] PANG Weixu, LI Ning, HUANG Xiaolong, Et al., Optimization of beam arrangement for tunable diode laser absorption tomography reconstruction based on fractional Tikhonov regularization, Acta Physica Sinica, 72, 3, pp. 314-324, (2023)
  • [7] XIE Zhengchao, WANG Fei, YAN Jianhua, Et al., Comparative studies of Tikhonov regularization and truncated singular value decomposition in the three-dimensional flame temperature field reconstruction, Acta Physica Sinica, 64, 24, pp. 21-28, (2015)
  • [8] SHAN Liang, ZHAO Tengfei, HUANG Huiyun, Et al., Flame 3D temperature field reconstruction based on Damped LSQR-LMBC, Acta Physica Sinica, 71, 4, pp. 21-32, (2022)
  • [9] LEE En-Jui, HUANG He, DENNIS John M, Et al., An optimized parallel LSQR algorithm for seismic tomography, Computers & Geosciences, 61, pp. 184-197, (2013)
  • [10] HINTON G E, SALAKHUTDINOV R R., Reducing the dimensionality of data with neural networks, Science, 313, 5786, pp. 504-507, (2006)
123