Prototype Early Warning Fire Detection System: Test Series 3 Results

Abstract

This work is a continuation of a multi-year effort to develop an early-warning fire detection system (EWFD) that is immune to nuisance alarms. The work was conducted under the Office of Naval Research-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. The results of this test series have demonstrated improved performance of the current probabilistic neural networks (PNN) alarm algorithm compared to previous prototype designs as well as alternate sensor/PNN combinations evaluated in this work. The current alarm algorithm resulted in better overall performance than the commercial smoke detectors by providing both improved nuisance source immunity with generally equivalent or faster response times. Areas of improvement have been identified. In particular, it is believed that the prototypes can be made to respond faster to long smoldering fires.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 19, 2001
Accession Number
ADA397831

Entities

People

  • Daniel T. Gottuk
  • Hung V. Pham
  • Jennifer T. Wong
  • Mark T. Wright
  • Susan L. Rose-Pehrsson

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Sensors

DTIC Thesaurus Topics

  • Algorithms
  • Carbon Dioxide Sensors
  • Carbon Monoxide
  • Carbon Monoxide Indicators
  • Chemistry
  • Combustion
  • Control Systems
  • Data Acquisition
  • Data Processing
  • Detection
  • Detectors
  • Dielectric Gases
  • Fire Detectors
  • Military Research
  • Neural Networks
  • Smoke Detectors
  • Warning Systems

Fields of Study

  • Engineering

Readers

  • Fire Suppression Systems Design.
  • Sensor Fusion and Tracking Systems.
  • Statistical inference.

Technology Areas

  • AI & ML