- Author
- Gottuk, D. T. | Hill, S. A. | Schemel, C. F. | Strehlen, B. D. | Rose-Pehrsson, S. L. | Shaffer, R. E. | Tatem, P. A. | Williams, F. W.
- Title
- Identification of Fire Signatures for Shipboard Multi-Criteria Fire Detection Systems. Interim Report. September 1997-February 1999.
- Coporate
- Hughes Associates, Inc., Baltimore, MD Naval Research Laboratory, Washington, DC
- Sponsor
- Office of Naval Research, Washington, DC
- Report
- NRL/MR/6180-99-8386, June 18, 1999, 111 p.
- Keywords
- shipboard fires | fire detection | fire detection systems | sensors | smoke detectors | neural networks
- Identifiers
- multi-signature; multrivariate analysis; probabilistic neural networks
- Abstract
- The Navy program Damage Control-Automation for Reduced Manning (DC-ARM) is focused on enhancing automation of ship functions and damage control systems. A key element to this objective is the improvement of current fire detection systems. As in many applications, it is desired to increase detection sensitivity, decrease the detection time and increase the reliability of the detection system through improved nuisance alarm immunity. Improved reliability is needed such that fire detection systems can provide quick remote and automatic fire suppression capability. The use of multi-criteria based detection technology continues to offer the most promising means to achieve both improved sensitivity to real fires and reduced susceptibility to nuisance alarm sources. An early warning fire detection system can be developed by properly .processing the output from sensors that measure multiple signatures of a developing fire or from analyzing multiple aspects of a given sensor output (e.g., rate of rise as well as absolute value). Although work has been done in the area of multi-signature detection, in many cases few sensor types have been examined (e.g., standard photoelectric smoke detectors and temperature or CO and CO2, for gas signatures) and only singular standard test sources have been used. This work was aimed at developing a broad database of signatures from real fire and nuisance alarm sources particular to onboard situations. Using this database and data in the literature, multi-criteria alarm algorithms are being developed. This report documents the FY 98-99 work including laboratory tests to identify signatures of realistic fire and nuisance alarm sources, review of typical fuel loadings and false alarm sources onboard USN ships and identification of potential discriminating alarm algorithm strategies. Based on the work performed to date, the report identifies the signatures that have the greatest potential value in an incipient fire detection system. The objective of this work was to determine the value of signatures from real fire and nuisance alarm sources as part of a multi-signature fire detection system. In addition, this work was aimed at identifying candidate signature combinations for potential prototype development.