25 September 2007 Optical infrared flame detection system with neural networks
Author Affiliations +
Abstract
A model for an infrared (IR) 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.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Javid J. Huseynov, Javid J. Huseynov, Shankar B. Baliga, Shankar B. Baliga, "Optical infrared flame detection system with neural networks", Proc. SPIE 6697, Advanced Signal Processing Algorithms, Architectures, and Implementations XVII, 66970L (25 September 2007); doi: 10.1117/12.731164; https://doi.org/10.1117/12.731164
PROCEEDINGS
10 PAGES


SHARE
Back to Top