- Author
-
Wright, M. T.
|
Gottuk, D. T.
|
Wong, J. T.
|
Rose-Pehrsson, S. L.
|
Hart, S. J.
|
Williams, F. W.
|
Tatem, P. A.
|
Street, T. T.
- Title
- Prototype Early Warning Fire Detection System: Test Series 1 Results. Interim.
- Coporate
- Naval Research Laboratory, Washington, DC
Hughes Associates, Inc., Baltimore, MD
- Sponsor
- Office of Naval Research, Arlington, VA
- Report
-
NRL/MR/6110-00-8486,
September 18, 2000,
76 p.
- Keywords
-
fire detection systems
|
warning systems
|
sensors
|
fire detection
|
ships
|
neural networks
|
response time
|
smoke detectors
|
smoke detection
|
fire detection
- Identifiers
- Early Warning Fire Detection (EWFD)
- Abstract
- This work is a continuation of a multi-year effort to develop an early-warning fire detection system that is highly immune to nuisance alarms. The work was conducted under the Office of Naval Research (ONR's) sponsored program Damage Control-Automation for Reduced Manning (DC-ARM) as part of a smart system capable of providing automated damage control. Over the past two years, efforts have focused on identifying appropriate sensors and candidate multivariate alarm algorithms. This is the first of several field tests that have been designed to generate data for prototype and algorithm development. For this test, two prototype detection systems were assembled and algorithms written to produce real-time responses and alarms. The prototypes were tested in real-time onboard the ex-USS SHADWELL, the Naval Research Laboratory's full scale fire research facility in Mobile, Alabama. The tests were conducted over the period of February 7-18, 2000. The prototype fire detectors were to exposed to both real fire and nuisance sources while installed onboard the ex-USS SHADWELL in a typical space. The prototype detectors (i.e., the group of sensors that make up the detector) were monitored using a standard data acquisition system interfaced with a desktop computer. The data was processed in real-time to provide an output indicating either normal or tire conditions. The real-time sensor data and the output of the detection alarm algorithm were also transmitted over a recently installed fiber optic Ethernet for remote monitoring. Sensor outputs as well as algorithm results were stored and used to access the areas of improvement needed compared to commercial off the shelf instruments installed on the ex-USS SHADWELL. Several additional sensors were included in the tests for consideration in future prototype systems. The system under development combines a multi-criteria (sensor array) approach with sophisticated data analysis methods. Together an array of sensors and a multivariate classification algorithm has the potential to produce an early warning fire detection system with a low nuisance alarm rate. Several sensors measuring different parameters of the environment produce a pattern or response fingerprint for an event. Multivariate data analysis methods can be trained to recognize the pattern of an important event such as a fire. Multivariate classification methods, such as neural networks, rely on the comparison of events (i.e., fires) with nonevents (i.e., background and nuisance sources). Variations in the response of sensors can be used to train an algorithm to recognize events when they occur. A key to the success of these methods is the approprite design of sensor arrays and training sets of data used to develop the algorithm. This test series included a variety of conditions that may be encountered in a real shipboard environment. Every effort was made to consider many representative fire situations and potential interference sources, including the use of Navy approved materials.