全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于Krawtchouk矩和支持向量机的火焰状态识别

DOI: 10.13334/j.0258-8013.pcsee.2014.05.004, PP. 734-740

Keywords: furnaceflamemonitoring,flameimage,featureextraction,staterecognition,Krawtchoukmoment,基金项目:国家自然科学基金项目(60872065),华中科技大学煤燃烧国家重点实验室开放基金项目(FSKLCC1001),江苏高校优势学科建设工程项目。

Full-Text   Cite this paper   Add to My Lib

Abstract:

监测炉膛火焰燃烧状态对防止锅炉爆管起着重要作用。为了进一步提高火焰图像特征提取的准确度和燃烧状态的识别率,文中将Krawtchouk矩引入火焰特征提取,提出了一种将Krawtchouk矩不变量与小波支持向量机相结合的火焰燃烧状态识别方法。首先计算火焰图像的Krawtchouk矩及Krawtchouk矩不变量,以此构造火焰图像的特征向量;然后根据训练样本的特征向量构造支持向量机,对火焰图像进行状态识别,并采用混沌小生境粒子群算法优化支持向量机中的核函数参数与惩罚因子,使其识别性能最优。大量实验结果表明:与基于Hu矩和支持向量机的方法、基于Zernike矩和支持向量机的方法相比,采用Krawtchouk矩不变量作为火焰图像的特征能更好地对火焰图像燃烧状态进行识别,识别率大大提高,且结果与实际情况相符。

References

[1]  Chacon Murguia M I,Perez Vargas F J.Thermal video analysis for fire detection using shape regularity and intensity saturation features[M].Springer Berlin Heidelberg:Pattern Recognition,2011:118-126.
[2]  吴占松.发光火焰图像处理技术在火焰监测上的应用[D].北京:清华大学,1998.
[3]  Luo Zixue,Zhou Huaichun.A combustion-monitoring system with 3-D temperature reconstruction based on flame-image processing technique[J].IEEE Transactions on Instrumentation and Measurement,2007,56(5):1877- 1882.
[4]  韩璞,张欣,王兵,等.基于神经网络的交互式炉膛火焰图像识别[J].中国电机工程学报,2008,28(20):22-26.Han Pu,Zhang Xin,Wang Bing,et al.Interactive method of furnace flame image recognition based on neural networks[J].Proceedings of the CSEE,2008,28(20):22-26(in Chinese).
[5]  Zhou X,Yu F,Wen Y,et al.Early fire detection based on flame contours in video[J].Information Technology Journal,2010,9(5):889-908.
[6]  Yingchun Wu,Xuecheng Wu,Kefa Cen.Novel methods for flame pulsation frequency measurement with image analvsis[C]//Springer Science Business Media,the United States,2012.
[7]  马骏,余岳峰,范浩杰.基于频谱分析和自组织神经网络的火焰燃烧诊断研究[J].动力工程,2004,24(6):852-856.Ma Jun,Yu Yuefeng,Fan Haojie.Research on flame detection and combustion diagnosis based on spectrum analysis and with self organized neural networks [J].Power Engineering,2004,24(6):852-856(in Chinese).
[8]  Chong C W,Raveendran P,Mukundan R.Translation invariants of Zernike moments[J].Pattern Recognition,2003,36(8):1765-1773.
[9]  Zhang L,Xiao W,Qian G,et al.Rotation,scaling,and translation invariant local watermarking technique with Krawtchouk moments[J].Chinese Optics Letters,2007,5(1):21-24.
[10]  吴海勇.基于两变量Krawtchouk矩的图像重建[J].中国图象图形学报,2008,13(9):1645- 1648.Wu Haiyong.Image reconstruction by Krawtchouk moments of two variables[J].Journal of Image and Graphics,2008,13(9):1645- 1648(in Chinese).
[11]  许志闻,纪政,郭哓新,等.基于小波神经网络的炉膛火焰识别和诊断[J].仪器仪表学报,2004(z3):376-379,383.Xu Zhiwen,Ji Zheng,Guo Xiaoxin,et al.Recognition and diagnosis of boiler flame based on wavelet neural network[J].Chinese Journal of Scientific Instrument,2004(z3):376-379,383(in Chinese).
[12]  刘禾.基于火焰图像和模糊神经网络的锅炉燃烧稳定性判别[J].仪器仪表学报,2008,29(6):1280-1284.Liu He.Judging boiler combustion stability based on flame image and fuzzy neural network[J].Chinese Journal o f Scientific Instrument,2008,29(6):1280-1284(in Chinese).
[13]  武广富,吕震中.粗糙集理论在火焰图像处理及状态识别中的应用[J].电力自动化设备,2007,27(5):84-87,121.Wu Guangfu,Lü Zhenzhong.Application of rough sets theory in flame image process and state recognition [J].Electric Power Automation Equipment,2007,27(5):84-87,121(in Chinese).
[14]  陈晓峰,王士同,曹苏群,等.基于模糊聚类的稳健支撑向量回归机及火焰图像处理[J].中国图象图形学报,2009,14(3):463-470.Chen Xiaofeng,Wang Shitong,Cao Suqun,et al.Fuzzy clustering based robust SVR and flame image processing [J].Journal of Image and Graphics,2009,14(3):463-470(in Chinese).
[15]  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,2004,24(2):185-190.Bai Weidong,Yan Jianhua,Chi yong,et al.A research on application of PCA and SVM to flame monitoring [J].Proceedings of the CSEE,2004,24(2):185-190(in Chinese).
[16]  韩斌,黄刚,王士同.基于边界矩和支持向量机的火焰识别算法[J].计算机应用研究,2009,26(7):2765-2770.Han Bin,Huang Gang,Wang Shitong.Flame recognition algorithm based on boundary moment and support vector machine[J].Application Research of Computers,2009,26(7):2765-2770(in Chinese).
[17]  耿强,田淑侠,黄太回,等.基于支持向量机和神经网络方法的应力腐蚀裂纹定量重构[J].电工技术学报,2010,25(10):196-199.Gen Qiang,Tian Shuxia,Huang Taihui,et al.Reconstruction of stress corrosion crack using neural network and support vector machine techniques [J].Transactions of China Electrotechnical Society,2010,25(10):196-199(in Chinese).
[18]  赵炯,樊养余.一种基于Pseudo—Zernike矩和SVM的目标识别快速算法[J].计算机应用研究,2010,27(12):4775-4777.Zhao Jiong,Fan Yangyu.Fast target recognition algorithm based on pseudo-zernike moment and support vector machine[J].Application Research of Computers,2010,27(12):4775-4777(in Chinese).

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133