典型文献
Design and implementation of gasifier flame detection system based on SCNN
文献摘要：
Flame detection is a research hotspot in industrial production, and it has been widely used in various fields. Based on the ignition and combustion video sequence, this paper aims to improve the accuracy and unintuitive detection results of the current flame detection methods of gasifier and in-dustrial boiler. A furnace flame detection model based on support vector machine convolutional neu-ral network ( SCNN) is proposed. This algorithm uses the advantages of neural networks in the field of image classification to process flame burning video sequences which needs detailed analysis. First-ly, the support vector machine ( SVM) with better small sample classification effect is used to re-place the Softmax classification layer of the convolutional neural network ( CNN) network. Second-ly, a Dropout layer is introduced to improve the generalization ability of the network. Subsequently, the area, frequency and other important parameters of the flame image are analyzed and processed. Eventually, the experimental results show that the flame detection model designed in this paper is more accurate than the CNN model, and the accuracy of the judgment on the flame data set collected in the gasifier furnace reaches 99. 53％. After several ignition tests, the furnace flame of the gasifier can be detected in real time.
文献关键词：
中图分类号：
作者姓名：
WU Jin;DAI Wei;WANG Yu;ZHAO Bo
作者机构：
School of Electronic Engineering,Xi'an University of Posts and Telecommunications,Xi'an 710121,P.R.China
文献出处：
引用格式：
[1]WU Jin;DAI Wei;WANG Yu;ZHAO Bo-.Design and implementation of gasifier flame detection system based on SCNN)[J].高技术通讯（英文版）,2022(04):401-410
A类：
unintuitive
B类：
Design,implementation,gasifier,flame,detection,system,SCNN,Flame,research,hotspot,industrial,production,has,been,widely,used,various,fields,Based,ignition,combustion,video,this,paper,aims,improve,accuracy,results,current,methods,boiler,furnace,model,support,vector,machine,convolutional,proposed,This,algorithm,uses,advantages,neural,networks,image,classification,burning,sequences,which,needs,detailed,analysis,First,better,small,sample,effect,place,Softmax,layer,Second,Dropout,introduced,generalization,ability,Subsequently,area,frequency,other,important,parameters,analyzed,processed,Eventually,experimental,show,that,designed,more,accurate,than,judgment,data,set,collected,reaches,After,several,tests,can,detected,real
AB值：
0.494631
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
