Optical infrared flame detection system with neural networks

被引：2
作者：
Huseynov, Javid J. [1 ,2 ]
Baliga, Shankar B. [2 ]
机构：
[1] Univ Calif Irvine, Sch Informat & Comp Sci, Irvine, CA 92697 USA
[2] Gen Monitors Inc, Lake Forest, CA 92630 USA
来源：
ADVANCED SIGNAL PROCESSING ALGORITHMS, ARCHITECTURES, AND IMPLEMENTATIONS XVII | 2007年 / 6697卷
关键词：
artificial neural networks; signal processing; infrared detectors; fire detection;
D O I：
10.1117/12.731164
中图分类号：
TH7 [仪器、仪表];
学科分类号：
0804 ; 080401 ; 081102 ;
摘要：
A model for an infrared (M) flame detection system using artificial neural networks (ANN) is presented. The joint time-frequency analysis (JTFA) in the form of a Short-Time Fourier Transform (STFT) is used for extracting relevant input features for a set of ANNs. Each ANN is trained using the backpropagation conjugate-gradient (CG) method to distinguish all hydrocarbon flames from a particular type of environmental nuisance and background noise. Signal saturation caused by the increased intensity of IR sources at closer distances is resolved by an adjustable gain control. A classification scheme with trained ANN connection weights was implemented on a digital signal processor for use in an industrial hydrocarbon flame detector.
引用
收藏
页数：10
相关论文
共 29 条
[11]  
*FACT MUT GLOB, RAD EN SENS FIR DET
[12]  
GOLDENBERG E, 1994, Patent No. 5373159
[13]  
Guterman H., 1994, Neural, Parallel & Scientific Computations, V2, P43
[14]  
Huseynov J, 2005, IEEE IJCNN, P1959
[15]  
HUSEYNOV JJ, 2007, Patent No. 7202794
[16]  
ISHII H, 1993, P 4 INT S FIR SAF SC, P761
[17]  
Johansson E. M., 1991, International Journal of Neural Systems, V2, P291, DOI 10.1142/S0129065791000261
[18]  
JONES WW, 2004, P 13 INT C AUT FIR D, P184
[19]   ANALYSIS OF SIGNATURE PATTERNS FOR DISCRIMINATING FIRE DETECTION WITH MULTIPLE SENSORS [J].
MILKE, JA ;
MCAVOY, TJ .
FIRE TECHNOLOGY, 1995, 31 (02) :120-136
[20]  
MILKE JA, 1995, P INT C AUT FIR DET, P213
123