New FL4000 Intelligent MSIR Flame Detection System
Fire monitoring and detection is one of the single most important safety challenges in all facilities involved with the production, refining and distribution of oil, natural gas and petrochemicals. Fire is also a critical threat in many other industries, including automotive food/beverage, pharmaceuticals, pulp/paper, printing, textiles, warehousing and more.
Accurate and reliable fire detection has always represented a technical challenge. The main difficulty lies in distinguishing between the spectral radiation emitted by actual flames and the radiation from nuisance sources. The failure to detect actual flames can be disastrous. False alarms are problematic too, initiating automated suppression equipment, consuming extinguishment materials and often requiring a complete plant shut-down and costly re-start sequence.
Until now, flame detection has been based on multi-spectral optical flame detectors integrated with expert signal processing systems. This type of system relies on an expert to design a fixed set of conditions. These devices meet basic flame detection needs, but are prone to false alarms caused by reflected sunlight, arc welding, lightning, hot piping, machinery, human operator movement and more.
Our new FL4000 flame detector is the industry’s first flame detection system to combine precision multi-spectral infrared (MSIR) flame sensing technology with highly intelligent neural network processors. The result is a breakthrough flame detector that provides the industry’s most reliable discrimination between actual flames and nuisance false alarm sources, such as arc welding, lightning, reflected sunlight and more.
Neural network technology (NNT) is based on artificial neural networks (ANN), which are mathematical models of biological neurons in the human brain that correlate given signal patterns with target flame conditions. The MSIR sensors and the neural network work together as an adaptive and intuitive decision-making mechanism with boundless optimization capability.
To detect flames, the FL4000’s MSIR detector makes use of four infrared sensors sampling different IR spectral wavelengths. Each sensor signal is sampled and then converted into digital format for initial signal pre-processing to extract time and frequency information. The time and frequency information are used by the FL4000’s proprietary neural network classification algorithm to identify if input IR signals are emitted from a flame or non-flame source. The flame or non-flame decision is then reported as an output via LEDs, relays, and MODBUS.
Built-in COPM (Continuous Optical Path Monitoring) self-diagnostic circuitry checks the optical path integrity (window cleanliness) and the detector’s electronic circuitry once every two minutes. Serial ports allow up to 128 units (247 using repeaters) to be linked up to a host computer using the MODBUS RTU protocol. With its highly reliable NNT flame discrimination algorithm, the FL4000 system is highly immune to false alarms while at the same time offering superior distance range and excellent field-of-view (FOV) characteristics.
For example, the FL4000 flame detector provides an increased detection range of 230 feet and is false alarm immune to arc welding at distances as close as 10 feet. In comparison, the major flame detectors on the market today feature a shorter detection range with a reduced false alarm immunity to arc welding. The FL4000 gives engineers a clear advantage in such applications.
In applications requiring a shorter range of detection from less than 60 feet to 120 feet, the FL4000 can be used with medium or low sensitivity settings while maintaining a 90-degree FOV. Operating with lower sensitivity settings also helps ensure the detector doesn’t respond to nuisance flame sources outside the desired area that is to be monitored -- again increasing false alarm immunity.
While offered as a standard product, the FL4000’s MSIR/NNT capabilities also allow users to customize the device to ignore difficult-to-recognize facility-specific false-alarm sources. Large companies with standardized plant design layouts can then replicate the lessons learned at a single facility to solve the same problem at all their facilities. This custom adaptive learning capability further expands the applications of the FL4000.
The FL4000 sets a new benchmark for performance, reliability, safety and value in flame detection. Accurately and reliably detecting flames has long been a technical challenge in the oil/gas, petrochemical and many other industries. The ability to differentiate spectral radiation emitted by actual flames from that emitted by background ambient radiation is absolutely crucial. Failure to do so results in either undetected fires, or more commonly, nuisance false alarms that interrupt operations, trigger suppression equipment, consume extinguishing materials, require resolution of the alarm condition and often operational or plant re-starts. The FL4000 is your next-generation solution in flame detection.
More information on the FL4000 including downloadable data sheet and brochure.
Copyright © 2005 General Monitors, Inc. All logos, brand and product names are registered trademarks of their perspective owners. All rights reserved. Questions or comments to email@example.com.