Visit the Magnetrol International web site

Flame detector learns about false alarms

A General Monitors product story
Edited by the Engineeringtalk editorial team Jan 12, 2006

Intelligent multi-spectral IR flame detector from General Monitors gives process and plant engineers a tool for protecting people, equipment and facilities from dangerous hydrocarbon flame sources.

With a multi-spectral infra-red flame sensor that incorporates neural network technology (NNT), the FL4000 Intelligent Multi-Spectral IR (MSIR) flame detection system from General Monitors gives process and plant engineers a tool for protecting people, equipment and facilities from dangerous hydrocarbon flame sources.

Until now, flame detection has been based on multi-spectral optical flame detectors integrated with expert signal processing.

This type of system relies on an expert to design a fixed set of conditions.

While these devices meet basic flame detection needs, they are prone to false alarms caused by reflected sunlight, arc welding, hot piping, machinery and other sources.

The FL4000 combines an optical MSIR sensor array with NNT processing.

NNT is based on artificial neural networks, which are mathematical models of biological neurons in the human brain that correlate given signal patterns with target flame conditions.

The optical IR sensor array and the neural network function together as an adaptive and intuitive decision-making mechanism.

The result is a flame detector that provides discrimination between actual flames and nuisance false alarm sources.

The MSIR detector uses four separate infra-red spectrums sampling different IR spectral areas to detect a flame.

Each sensor's analogue signals are sampled and then converted into digital form for initial signal pre-processing to extract time and frequency information.

The time and frequency information is used by the 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.

Range is up to 70m and field-of-view characteristic is 100 at 15m.

It provides false alarm immunity to arc welding as close as 3m away.

Built-in continuous optical path monitoring self-diagnostic circuitry checks the optical path integrity and the detector's electronic circuitry once every two minutes.

Serial ports allow up to 128 units (247 using repeaters) to be linked to a host computer using the Modbus RTU protocol.

Applications are in the oil, gas, petrochemical and other industries.

The ability to differentiate spectral radiation emitted by actual flames from that emitted by background ambient radiation is 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.

Send to a friend Send to a friend
Print this page Print this page
Bookmark this page Bookmark this page

Not what you're looking for? Search the site.

Back to top Back to top

Google Ads

 

Contact General Monitors

Contact General Monitors

Company profile and news

Related Stories

Contact General Monitors

 

Newsletter sign up

Request your free weekly copy of the Engineeringtalk email newsletter ...

Sign up now Sign up now

Visit the Magnetrol International web site

Articles by product category

All suppliers A - Z

A Pro-talk Publication

A Pro-talk publication