English  |  正體中文  |  简体中文  |  Items with full text/Total items : 2737/2828
Visitors : 341782      Online Users : 31
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search
LoginUploadHelpAboutAdminister

Please use this identifier to cite or link to this item: http://ir.lib.stu.edu.tw:80/ir/handle/310903100/1240

Title: 應用於火災偵測之無線感測網路系統
Applications of Wireless Sensor Networks on Fire Detection and Positionization
Authors: 王柏憲
Bo-Sian Wang
Contributors: E-Liang Chen
資訊工程學系
Keywords: 無線感測網路;火災偵測;火焰辨識
Wireless Sensor Networks;Fire detection;Flame recognition
Date: 2009
Issue Date: 2011-05-24 15:11:58 (UTC+8)
Publisher: 高雄市:[樹德科技大學資訊工程學系]
Abstract: 本論文所提出火災偵測系統整合無線感測網路、資通訊技術、簡訊技術以及
語音技術TTS 能在火災現場中提供火焰定位與溫度監控功能,藉由溫度差值演算
法(FLATD)來判斷火焰產生的位置。透過溫度異常判定演算法(TAA)進行溫度監
控,監控室內的溫度是否有發生異常狀況,以便發出警報。在FLATD 我們使用溫
度的差值作為特徵,藉由此特徵透過溫度差值區間表,我們可以推斷出火焰的位
置,達到定位的效果。根據實驗結果顯示,我們的方法在11 區間有最好的準確度
高達到84.84%,誤差最大的距離6.5%,相較於10 區準確度達到78.78%間,誤
差最大的距離70 公分,準確度高出6.06%,誤差最大的距離少0.5%。
本論文提供溫度監控方法之溫度異常判定演算法(TAA),使用非接觸式紅外線
溫度感測器裝置在天花板上,監控室內溫度判斷溫度是否發生異常。在TAA 中,
我們探討幾種火焰擴散的情境,(1)火焰持續擴散到整個區域,(2)火焰擴散一定程
度後停止,(3)溫度異常雜訊,從結果來看TAA 能夠準確判斷(1)(2)兩種情境。為
驗證所提演算法對於雜訊的容忍程度,在本篇論文中利用隨機機率模型產生大量
的溫度異常節點用以干擾TAA 的計算,由結果我們可以發現TAA 在70~80%以上
的雜訊干擾的情況下才會發出警報,低雜訊密度時可以完整過濾掉雜訊,若同一
節點雜訊密度過高才會將它視為是火焰的擴散。
In this thesis, applications of Wireless Sensor Networks integrating with
communication technology, sensor, and voice-to-speech (TTS) technology are presented.
The presented system detects effectively the existence and the possible position of fire
as well as monitors temperature in the neighborhood according the design fire-locating
algorithm based on temperature difference (FLATD), to estimate the location of the
flame. In addition, a temperature anomaly-detection algorithm(TAA) is proposed to
monitor the regional temperature distribution and estimate the flame possibility. Once a
flame condition is detected, SMS and audio alarms are issued to the related users. In
FLATD we use the characteristics of the temperature difference as an approximation
indicating the fire location. According to the experimental results, it has shown that our
approach achieves about the ranging accuracy of 84.84% with the largest error of 65 cm.
In another case, the ranging accuracy is about 78.78% with an error of 70 cm.
In the monitoring of regional temperature distribution, we explore several cases of
flame-spread, (1) flame continuously spread to the entire region, (2) the flame spread in
a fix and limited region (3) possible noise introduced to sensor. The effectiveness of
TAA in (1) and (2) are simulated to confirm. Regarding to (3), random noise is
introduced to assist the evaluation of noise effect on TAA. We find that TAA works well
even in case of 80% noise strength.
Appears in Collections:[資訊工程系(所) ] 博碩士論文

Files in This Item:

File Description SizeFormat
應用於火災偵測之無線感測網路系統__臺灣博碩士論文知識加值系統.htm國圖105KbHTML509View/Open


All items in STUAIR are protected by copyright, with all rights reserved.

 


無標題文件

著作權政策宣告:

1.

本網站之數位內容為樹德科技大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,惟仍請適度,合理使用本網站之內容,以尊重著作權人之權益。商業上之利用,則請先取得著作權人之授權。
 
2. 本網站之製作,已盡力防止侵害著作權人之權益,如仍發現本網站之數位內容有侵害著作權人權益情事者,請權利人通知本校護人員(clairhsu@stu.edu.tw),維護人員將立即採取移除該數位著作等補救措施。
 
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback