融合火焰辐射图像和CNN的电站锅炉温度场在线监测研究

周科; 王健; 任延南; 张越; 戴轩; 梁传龙; 金全; 闫伟杰

doi:10.19666/j.rlfd.202504094

欢迎来到能源电力期刊网！

您当前的位置：

首页 >

文章列表页 >

融合火焰辐射图像和CNN的电站锅炉温度场在线监测研究

热能科学研究 | 更新时间：2026-03-18

- 融合火焰辐射图像和CNN的电站锅炉温度场在线监测研究
- 融合火焰辐射图像和CNN的电站锅炉温度场在线监测研究
- 热力发电 2026年55卷第1期页码：142-151
- 作者机构：
  
  1. 西安热工研究院有限公司
  2. 华能国际电力股份有限公司丹东电厂
  3. 南京理工大学能源与动力工程学院
- 作者简介：
- 基金信息：
  
  国家自然科学基金面上项目（52176144）~~
- DOI：10.19666/j.rlfd.202504094
  中图分类号： TM621.2;TP391.41
- 纸质出版：2026
- 稿件说明：
移动端阅览
[1]周科,王健,任延南,等.融合火焰辐射图像和CNN的电站锅炉温度场在线监测研究[J].热力发电,2026,55(01):142-151.
[1]周科,王健,任延南,等.融合火焰辐射图像和CNN的电站锅炉温度场在线监测研究[J].热力发电,2026,55(01):142-151. DOI： 10.19666/j.rlfd.202504094.

DOI：10.19666/j.rlfd.202504094.

摘要

现有火焰辐射图像测温技术因探测器镜头结焦问题导致测量误差，亟需一种能够智能消除结焦干扰的在线监测方法。提出一种融合火焰辐射图像和卷积神经网络（convolutional neural network

CNN）的电站锅炉温度场在线监测方法。首先，通过黑体炉标定探测器，建立探测器单色辐射强度与图像强度的关系；然后，设计适合火焰图像处理的CNN模型，并利用现场采集锅炉的未结焦火焰辐射强度图像构建学习集，建立火焰辐射强度图像还原模型；最后，利用模拟结焦火焰图像验证该方法的测量精度。研究结果表明：测温精度随着学习集数量的减少而降低，学习集火焰图像数量为3 000张时，测温相对误差为1.4%；测温精度随着结焦面积的增大而降低，结焦面积为30%时，测量温度的最大相对误差为0.7%。此外，研究表明学习集训练探测器的模型计算其他探测器结焦图像时，测温误差会增大，最大相对误差达34.6%。这表明应用该方法时需对每个燃烧器的探测器单独训练。研究方法能够智能消除结焦对火焰辐射图像的干扰，实现高精度温度场在线监测，为电站锅炉的安全运行和燃烧优化提供了可靠的技术支持。

Abstract

The existing flame radiation image temperature measurement technology has measurement errors due to the coking problem of the detector lens. There is an urgent need for an online monitoring method that can intelligently eliminate the coking interference. An online monitoring method for the temperature field of power station boilers that integrates flame radiation images and convolutional neural network(CNN) is proposed. Firstly

the detector is calibrated via a blackbody furnace

and the relationship between the monochromatic radiation intensity of the detector and the image intensity is established. Secondly

a CNN model suitable for flame image processing is designed

and the training set is constructed by using the non-coking flame radiation intensity images of the boiler collected on-site to establish the flame radiation intensity image restoration model. Finally

the measurement accuracy of this method is verified by using the simulated coking flame images. The results show that the temperature measurement accuracy decreases with the reduction of the number of training sets. When the number of flame images in the learning set is 3 000

the relative error of temperature measurement is 1.4%. The temperature measurement accuracy decreases as the coking area increases. When the coking area is 30%

the maximum relative error of temperature measurement is 0.7%. Furthermore

studies show that when the model of the detector trained by the learning set calculates the coked images of other detectors

the temperature measurement error will increase

with the maximum relative error reaching 34.6%. This indicates that when applying this method

the detectors of each burner need to be trained separately. The proposed method can intelligently eliminate the interference of coking on the flame radiation image

achieve high-precision online monitoring of the temperature field

and provide reliable technical support for the safe operation and combustion optimization of power station boilers.

关键词

Keywords

references

LI T J, HU Z C, YAN W J, et al. In situ measurement of cross-section temperature field of pulverized coal boiler based on solving radiative transfer equation using a single image sensor[J]. Proceedings of the Combustion Institute,2024, 40(1/4):105655.

亚云启.基于光谱分析和图像处理的炉膛火焰温度检测及燃烧诊断[D].徐州:中国矿业大学, 2017:1.YA Yunqi. Flame temperature measurement and combustion diagnosis of furnace based on spectral analysis and image processing[D]. Xuzhou:China University of Mining and Technology, 2017:1.

李框宇,高鹏,杜峰,等.基于火焰图像分析的1 000 MW电站锅炉炉膛温度及发射率同时测量研究[J].能源研究与利用, 2021(5):2-7.LI Kuangyu, GAO Peng, DU Feng, et al. Study on simultaneous measurement of furnace temperature and emissivity of 1 000 MW power plant Boiler based on flame image analysis[J]. Energy Research&Utilization.2021(5):2-7.

胡智超.基于辐射逆问题分析的大型炉膛火焰温度场及辐射参数同时测量研究[D].徐州:中国矿业大学,2023:1.HU Zhichao. Simultaneous measurement of temperature field and radiation parameters of large furnace based on inverse radiation problem analysis[D]. Xuzhou:China University of Mining and Technology, 2023:1.

AKRAM M W, LI G, JIN Y, et al. CNN based automatic detection of photovoltaic cell defects in electroluminescence images[J]. Energy, 2019, 189:116319.

ZHAO D F, TIAN C Y, FU Z J, et al. Multi scale convolutional neural network combining BiLSTM and attention mechanism for bearing fault diagnosis under multiple working conditions[J]. Scientific Reports, 2025,15(1):13035.

ZHANG X L, CUI J, LIU H J, et al. Weed identification in soybean seedling stage based on optimized faster RCNN algorithm[J]. Agriculture, 2023, 13(1):175.

GAO J, FRENCH A P, POUND M P, et al. Deep convolutional neural networks for image-based convolvulus sepium detection in sugar beet fields[J]. Plant Methods, 2020, 16(1):29.

KALBANDE K, PATIL W V, SYSTEMS D. The convolutional neural network for plant disease detection using hierarchical mixed pooling technique with smoothing to sharpening approach[J]. International Journal of Computing and Digital Systems, 2023, 14(1):357-377.

GILL H S, BATH B S, SINGH R, et al. Wheat crop classification using deep learning[J]. Multimedia Tools and Applications, 2024, 83(35):82641-82657.

LU S, LU Z, AOK S, et al. Fruit classification based on six layer convolutional neural network[C]//Proceedings of the 2018 IEEE 23rd International Conference on Digital Signal Processing(DSP). IEEE, 2018:1.

YADAV D P, KUMAR D, JALAL A S, et al.Morphological diagnosis of hematologic malignancy using feature fusion-based deep convolutional neural network[J]. Scientific Reports, 2023, 13(1):16988.

HAN J H, JI S Y, KIM M, et al. Diagnosis of trigeminal neuralgia based on plain skull radiography using convolutional neural network[J]. Scientific Reports, 2025,15(1):18888.

KASSUBEK J, ROSELLI F, WITZEL S, et al.Hypothalamic atrophy in primary lateral sclerosis, assessed by convolutional neural network-based automatic segmentation[J]. Scientific Reports, 2025, 15(1):1551.

KHAIRANDISH M O, SHARMA M, JAIN V, et al. A hybrid CNN-SVM threshold segmentation approach for tumor detection and classification of MRI brain images[J].Innovation and Research in Biomedical Engineering:IRBM, 2022, 43(4):290-299.

LI N J, CHANG F L. Video anomaly detection and localization via multivariate Gaussian fully convolution adversarial autoencoder[J]. Neurocomputing, 2019, 369:92-105.

TOTH P, GARAMI A, CSORDAS B. Image-based deep neural network prediction of the heat output of a step-grate biomass boiler[J]. Applied Energy, 2017, 200:155-169.

闫伟杰.基于光谱分析和图像处理的火焰温度及辐射特性检测[D].武汉:华中科技大学, 2014:1.YAN Weijie. Measurement of flame temperature and radiative properties based on spectral analysis and image processing[D]. Wuhan:Huazhong University of Science and Technology, 2014:1.

闫乐乐,李辉,邱聚能,等.基于区域对比度和SSIM的图像质量评价方法[J].应用光学, 2015(1):58-63.YAN Lele, LI Hui, QIU Juneng, et al. Image quality assessment method based on regional contrast and structural similarity[J]. Journal of Applied Optics, 2015(1):58-63.

赵岩,孟丽茹,王世刚,等.符合人眼视觉感知特性的改进PSNR评价方法[J].吉林大学学报(工学版), 2015,45(1):309-313.ZHAO Yan, MENG Liru, WANG Shigang, et al. Improved PSNR evaluation method consistent with human visual perception[J]. Journal of Jilin University(Engineering and Technology Edition), 2015, 45(1):309-313.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

汽轮机转子温度场有限元法简化计算模型

基于数字图像处理和神经网络的炉膛温度场测量及燃烧诊断方法的研究

一台220t/h燃煤锅炉防结渣方案研究

太阳能烟囱发电试验装置内流场的CFD模拟研究

直接空冷凝汽器考核工况的全厂数值模拟