Font Size: a A A

Research On The Key Technologies Of Fire Warning And Alarm In The Centralized Area Of Combustible Of The Same Type

Posted on:2018-07-10Degree:MasterType:Thesis
Country:ChinaCandidate:C ZhangFull Text:PDF
GTID:2348330518998090Subject:Computer Science and Technology
Abstract/Summary:PDF Full Text Request
Fire to the human society has brought countless disasters, especially in the same type of flammable concentration of fire in the area is quite fierce, not easy to fight. This paper explores a set of mature solutions, can detect the fire quickly, and timely warning alarm.The main work of this paper is as follows:(1) This paper is according to the research results of many famous scientists, experience of Infrared Air-to-Air Missile,based on HgCdTe infrared sensor, put forward the fire detecting of the same type of flammable materials. This paper, converting the idea of the radio direction finding to the idea of fire dectecting, using the scheme of fire location based on the relative angle of mutiple fire detection equipment,solves the disadvantages of current solution not be able to position the fire outdoor.(2) This paper designs a more analytical solution of multi sensor data fusion for the sametype of mature combustible centrally located large span warehouse,the scheme makes full use of BP neural network and ART neural network and its advantages, combined with the characteristics of early information extraction, strictly according to relevant national standards,to achieve a double precision and improve efficiency. At the same time, using a CPU and a plurality of GPU in a common workstation, aiming at the defects of the slow speed of the BP neural network, putting forward parrllel computing, it can improve the computing efficiency and reduce the hardware cost.(3) In view of the design of a number of key technologies there is no fire detection equipment supporting this unique and innovative design based on the proposed design, gives the design scheme of fire detection equipment complete and the key part of the circuit in detail and design of hardware and software that, eventually complete results are given.
Keywords/Search Tags:fire alarm, fire location, infrared technology, multi-sensor, neural network
PDF Full Text Request
Related items