In this article Rick Jeffress, Director, Business Development, Fike Corporation, outlines how the use of advanced video analytics can help engine room operators reduce the incidence of fire caused by oil leakage.
Oil leakage hitting hot spots on engines is the most common cause of engine room fires on board ships. According to DNV GL statistics, more than 60% of all engine room fires have been initiated by a hot spot and of these fires over 50% have been caused by oil leakage. Fires caused by oil leakage are often more serious than fires caused by other factors.
The fire detection and alarm system activation and crew actions are, by their nature, a reaction to the event. The fire has to take hold and therefore have caused damage before remedial action takes place. At the very least an engine room fire will cause severe disruption to the operation of the ship.
Oil leakage fires are most likely to be caused by oil mist, which can be formed through minute leaks in pressurized oil lines or when oil hits a hot surface and boils generating a mist. Detection at this stage would create a pre-alarm warning and remedial action could be taken immediately to stop a fire occurring.
Oil mist detection devices have existed for some time including projected beam detectors, aspirating detectors and fixed detectors. There are several disadvantages of these technologies, not least because of the complex and demanding environment that an engine room creates for oil mist detection. There is typically a requirement for many detectors to be installed around the engine room, filters to be regularly replaced and sensitivity issues. A technology that overcomes these limitations is Fike Video Analytics. Currently, there are many shipboard applications of video analytics as oil mist detection systems. For example, a major cruise line requires all of its ships to monitor engine room cameras with video analytics.
Fike Video Analytics analyses video from off-the-shelf video cameras to detect visible oil mist/spray in early stages and provides an alarm with live video to the engine control room, bridge, or anywhere on the ship. To achieve the fast response required to minimize potential fire risks, the video analytics uses visual imaging, artificial intelligence and a neural network for fast processing of information. The software learns the cameras’ field of view and monitors for characteristics of oil mist or spray known to cause flame or explosion.
The system incorporates detection algorithms for smoke (oil mist or spray), flame, reflected light and motion. The algorithms can be used independently or in any combination. Each algorithm can be configured with detection/blocking zones, sensitivities, time delays, etc., to target detection. A small number of cameras can cover a wide area, or complex environments typical of engine rooms.
The video can be recorded for post-incident analysis and use video streamed from existing, off-the-shelf cameras.
For shipboard applications, video analytics are commonly used in the following areas:
- Diesel Generators and Diesel Propulsion Engines
- Oil Fired Boilers
- Incinerator Room
- Purifiers and fuel modules
- Emergency Diesel Generator
- Auxiliary Emergency Diesel Generator
- Mooring Deck
The use of video analytics is now a proven solution for engine room fire protection as well as other shipboard applications. A camera network combined with video analytics creates a highly efficient means for rapidly detecting oil mist, a precursor to a potential fire or explosion. The system can be monitored by shipboard personnel and linked to automation and safety management systems, allowing critical time to take action before disaster occurs.
By Rick Jeffress, Director, Business Development, Fike Corporation
The views presented hereabove are only those of the author and not necessarily those of SAFETY4SEA and are for information sharing and discussion purposes only.
[divider]
Rick Jeffress resides in Houston, Texas and oversees global business and application development of the Fike Video Analytics detection product line. He has over 24 years of industrial and marine fire protection experience with complex fire alarm and suppression systems’ design and application for marine vessels, petrochemical and power plants and offshore oil and gas projects.
Rick worked closely with a major cruise line technical safety staff, through pilots and onboard testing, to apply Fike Video Analytics to the marine engine room environment for early detection of atmospheric oil mist, smoke, flame and reflected flame. The technology is now part of safety directive for some of the world’s largest cruise lines.