Neural-net IR flame detector

FL4000 intelligent multi-spectral IR (MSIR) flame-detection system is designed to protect people, equipment, and facilities from dangerous hydrocarbon flame sources. Next-generation device combines neural network technology (NNT) with an advanced optical MSIR to create an adaptive, intuitive decision-making mechanism that can reliably discriminate between flames and nuisance false alarm sources.

By Staff February 1, 2006

FL4000 intelligent multi-spectral IR (MSIR) flame-detection system is designed to protect people, equipment, and facilities from dangerous hydrocarbon flame sources. Next-generation device combines neural network technology (NNT) with an advanced optical MSIR to create an adaptive, intuitive decision-making mechanism that can reliably discriminate between flames and nuisance false alarm sources. (NNT is based on artificial neural networks, which are mathematical models of biological neurons found in the human brain that correlate given signal patterns with target flame conditions.) FL4000’s MSIR detector uses four infrared spectra, sampling different IR spectral areas to detect a flame. Flame or non-flame decisions are reported as an output via LEDs, relays, and Modbus. www.generalmonitors.com General Monitors