基于支持向量机的多负荷燃烧器火焰状态识别

钱相臣, 马赟, 徐伟程, 付伟

计量学报 ›› 2025, Vol. 46 ›› Issue (11) : 1568-1573.

PDF(1252 KB)
PDF(1252 KB)
计量学报 ›› 2025, Vol. 46 ›› Issue (11) : 1568-1573. DOI: 10.3969/j.issn.1000-1158.2025.11.03
热学计量

基于支持向量机的多负荷燃烧器火焰状态识别

作者信息 +

Support Vector Machine Based Burner Flame States Identification under Multiple Loading Conditions

Author information +
文章历史 +

摘要

燃烧器火焰状态的有效监测对燃煤电厂的安全生产和节能减排都具有重要作用。现有的火检系统主要以检测火焰是否存在为主要任务,不能对火焰状态进行准确判断。因此以实际条件下获取到的火焰图像为对象,以支持向量机作为基础分类器,提出了一种融合火焰图像颜色和轮廓特征且使用改进粒子群优化算法进行参数寻优的火焰状态识别方法。实验结果表明,在数据量充足的前提下,所提出的方法对3种不同负荷状态下的燃烧器火焰图像分类准确率达到99%以上,且改进后的参数寻优算法较之传统算法有更好的性能,同时在低数据集容量情况下表现更好。

Abstract

The effective monitoring of burner flame status in coal-fired power plants is crucial to production safety, energy-saving and emission reduction. Existing fire detection systems mainly focus on detecting the presence of flame as the main task, and cannot make accurate judgments on the state of the flame. Therefore, a method for determining the flame states with different load conditions is proposed. The support vector machines are used as a basic classifier to combine the flame color and contour characteristics, which are derived from the flame images obtained in an actual power plant. Furthermore, an improved particle swarm optimization algorithm is employed for parameter optimization. Experimental results demonstrate that with sufficient data, the proposed method achieves a classification accuracy of more than 99% on flame images with three load conditions. In addition, the improved parameter optimization algorithm outperforms traditional methods, and the proposed method exhibits better performance with low dataset capacity.

关键词

火焰状态监测 / 燃烧诊断 / 数字图像处理 / 支持向量机 / 粒子群优化算法

Key words

flame states monitoring / combustion diagnosis / digital image processing / support vector machine / particle swarm optimization algorithm

引用本文

导出引用
钱相臣, 马赟, 徐伟程, . 基于支持向量机的多负荷燃烧器火焰状态识别[J]. 计量学报. 2025, 46(11): 1568-1573 https://doi.org/10.3969/j.issn.1000-1158.2025.11.03
QIAN Xiangchen, MA Yun, XU Weicheng, et al. Support Vector Machine Based Burner Flame States Identification under Multiple Loading Conditions[J]. Acta Metrologica Sinica. 2025, 46(11): 1568-1573 https://doi.org/10.3969/j.issn.1000-1158.2025.11.03
中图分类号: TB94   

参考文献

[1]
ZHOU C WANG Y JIN Q, et al. Mechanism analysis on the pulverized coal combustion flame stability and NO x emission in a swirl burner with deep air staging[J]. Journal of the Energy Institute201992(2): 298-310.
[2]
CHI T ZHANG H YAN Y, et al. Investigations into the ignition behaviors of pulverized coals and coal blends in a drop tube furnace using flame monitoring techniques[J]. Fuel201089(3): 743-751.
[3]
BURBANO H J PAREJA J AMELL A A. Laminar burning velocities and flame stability analysis of H2/CO/air mixtures with dilution of N2 and CO2 [J]. International Journal of Hydrogen Energy201136(4): 3232-3242.
[4]
WANG X CHEN H SULTAN U, et al. A brief review of the combustion diagnosing techniques for coal‑fired boilers of power plants in China[J]. IEEE Access20197: 126127-126136.
[5]
华彦平, 邹煜, 吕震中. 现代燃煤电站锅炉火焰检测综述[J]. 热能动力工程200116(1): 1-5.
HUA Y P ZOU Y LU Z Z. A review of boiler flame detection in modern coal‑fired power stations[J]. Thermal Power Engineering200116(1): 1-5.
[6]
SUN D LU G ZHOU H, et al. Quantitative assessment of flame stability through image processing and spectral analysis[J]. IEEE Transactions on Instrumentation and Measurement201564(12): 3323-3333.
[7]
LU G YAN Y CORNWELL S, et al. Impact of co‑firing coal and biomass on flame characteristics and stability[J]. Fuel200887(7): 1133-1140.
[8]
PAN J LIBERA J A PAULSON N H, et al. Flame stability analysis of flame spray pyrolysis by artificial intelligence[J]. The International Journal of Advanced Manufacturing Technology2021114(7-8): 2215-2228.
[9]
XU W YAN Y LU G, et al. Quantitative Assessment of Burner Flame Stability Through Digital Image Processing[J]. IEEE Transactions on Instrumentation and Measurement202271: 1-13.
[10]
HUANG Y YAN Y LU G, et al. On‑line flicker measurement of gaseous flames by image processing and spectral analysis[J]. Measurement Science and Technology199910(8): 726-733.
[11]
SUN D LU G ZHOU H, et al. A simple index based quantitative assessment of flame stability[C]// IEEE. 2013 IEEE International Conference on Imaging Systems and Techniques (IST). Beijing, China, 2013: 190-193.
[12]
白卫东, 严建华, 池涌, 等. PCA和SVM在火焰监测中的应用研究[J]. 中国电机工程学报200424(2): 185-190.
BAI W D YAN J H CHI Y, et al. A Reserch on Application of PCA and SVM to Flame Monitoring[J]. Proceedings of CSEE200424(2): 185–190.
[13]
盛杨, 刘禾. 基于支持向量机的炉膛火焰灭火判别方法研究[J]. 现代电力200724(2): 66-69.
SHENG Y LIU H. Furnace Outfire Judgement Based on Support Vector Machine[J]. Modern Electric Power200724(2): 66-69.
[14]
卫成业, 严建华, 商敏儿, 等. 基于炉内火焰图像的燃烧诊断[J]. 动力工程200323(3): 2420-2427.
WEI C Y YAN J H SHANG M E, et al. Combustion diagnostics based on furnace flame images[J]. Power Engineering200323(3): 2420-2427.
[15]
白晓静, 卢钢, 闫勇. 基于多尺度颜色小波纹理特征的火焰图像分割[J]. 计算机工程与应用201753(9): 213-219.
BAI X J LU G YAN Y. Flame image segmentation using multiscale color and wavelet‑based texture features[J]. Computer Engineering and Applications201753(9): 213-219.
[16]
蒋先刚, 张盼盼, 盛梅波. 基于时空块协方差融合特征的火焰识别方法[J]. 计算机工程与应用201652(17): 208-214.
JIANG X G ZHANG P P SHENG M B. Flame recognition method based on temporal‑spatial block covariance matrix blending feature[J]. Computer Engineering and Applications201652(17): 208-214.
[17]
LYU W, LU W MA M. No‑reference quality metric for contrast-distorted image based on gradient domain and HSV space[J]. Journal of Visual Communication and Image Representation202069: 102797.
[18]
BENCO M HUDEC R KAMENCAY P, et al. An advanced approach to extraction of colour texture features based on GLCM[J]. International Journal of Advanced Robotic Systems201411(7): 104.

基金

国家自然科学基金(51827808)

PDF(1252 KB)

Accesses

Citation

Detail

段落导航
相关文章

/