• DocumentCode
    2477571
  • Title

    Study on Fire Detection Model Based on Fuzzy Neural Network

  • Author

    Guo, Quanmin ; Dai, Junjie ; Wang, Jian

  • Author_Institution
    Sch. of Electron. Inf. Eng., Xi´´an Technol. Univ., Xi´´an, China
  • fYear
    2010
  • fDate
    22-23 May 2010
  • Firstpage
    1
  • Lastpage
    4
  • Abstract
    The fire signal detection is a non-structural problem and difficult to be precise described by mathematical model, which increase the difficulty of fire detection. According to the special type of signal detection technique such as fire signal detection, a fire detection model based on fuzzy-neural network is presented. This paper described the design method of the model, as well as its learning algorithm. In standard fire test rooms, simulation experiments were carried out for smoldering fire SH1 and flaming fire SH3 of the china national standard test fires, the model can make right judgment. Theory analysis and simulation study show that the model combines the advantages of fuzzy system and neural network, and improves the intelligence of fire detection, has a stronger ability to adapt the environment. It effectively solves the problems of mistake and failure in the fire alarm, and improves the sensibility of fire detection.
  • Keywords
    fires; flames; fuzzy logic; fuzzy neural nets; signal detection; signal processing; unsupervised learning; china national standard test fires; fire signal detection model; flaming fire SH3; fuzzy neural network; learning algorithm; smoldering fire SH1; standard fire test rooms; Analytical models; Design methodology; Fires; Fuzzy neural networks; Fuzzy systems; Intelligent networks; Mathematical model; Neural networks; Signal detection; Testing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Systems and Applications (ISA), 2010 2nd International Workshop on
  • Conference_Location
    Wuhan
  • Print_ISBN
    978-1-4244-5872-1
  • Electronic_ISBN
    978-1-4244-5874-5
  • Type

    conf

  • DOI
    10.1109/IWISA.2010.5473248
  • Filename
    5473248