發(fā)布時(shí)間：2018-09-18 20:43

【摘要】：火災(zāi)是人類生活中主要的事故之一,會(huì)給人類造成巨大的人員傷亡和財(cái)產(chǎn)損失,人類一直與火災(zāi)進(jìn)行著不屈不撓的斗爭(zhēng)。隨著電子工程、通信技術(shù)及計(jì)算機(jī)技術(shù)等的發(fā)展,人類已經(jīng)可以獲得在與火災(zāi)戰(zhàn)斗中取得勝利的強(qiáng)大武器。在一些重要建筑中安裝分布式火災(zāi)監(jiān)測(cè)系統(tǒng)后,火災(zāi)發(fā)展的相關(guān)信息可以實(shí)時(shí)提供給火災(zāi)應(yīng)急管理和滅火救援戰(zhàn)斗指揮人員,以采取有效的應(yīng)對(duì)措施。然而,目前采用的火災(zāi)報(bào)警系統(tǒng)多數(shù)僅僅給出火災(zāi)報(bào)警信號(hào),在后續(xù)整個(gè)火災(zāi)的應(yīng)急救援中均棄而不用。一方面,采用單種火災(zāi)探測(cè)傳感器僅僅描述火災(zāi)發(fā)展過程的部分信息,因此會(huì)導(dǎo)致很高的誤報(bào)和漏報(bào)情況,需要發(fā)展采用多傳感器技術(shù)的火災(zāi)探測(cè)及監(jiān)測(cè)技術(shù)。另一方面,采用多傳感器后盡管可以給出整個(gè)火災(zāi)發(fā)展過程的詳細(xì)信息,但是直接采用大量的原始數(shù)據(jù)不易獲取對(duì)火災(zāi)發(fā)展?fàn)顩r的直觀理解,并會(huì)迅速導(dǎo)致信息過載。所以需要在現(xiàn)有火災(zāi)探測(cè)技術(shù)基礎(chǔ)上發(fā)展基于多傳感器信息融合技術(shù)的火災(zāi)監(jiān)測(cè)系統(tǒng)。 本研究的主要目的是發(fā)展一個(gè)基于多傳感器信息融合技術(shù)的火災(zāi)危險(xiǎn)度分布確定系統(tǒng),該系統(tǒng)旨在輔助火災(zāi)監(jiān)測(cè)、火災(zāi)應(yīng)急管理、火災(zāi)救援和滅火戰(zhàn)斗。在采用來自不同傳感器的信息后,系統(tǒng)對(duì)火災(zāi)發(fā)出有效報(bào)警,并可以提供建筑內(nèi)不同區(qū)域的危險(xiǎn)度分布信息。通過采用信息融合技術(shù),降低了火災(zāi)應(yīng)急管理、火災(zāi)救援及滅火戰(zhàn)斗等過程中的冗余信息量。 首先,提出了在多傳感器火災(zāi)探測(cè)中進(jìn)行火災(zāi)探測(cè)特征組合選取的模型。模型基于信息熵理論中的互信息的概念,采用最大相關(guān)和最小冗余性的準(zhǔn)則選取火災(zāi)探測(cè)特征。與傳統(tǒng)進(jìn)行大量不同火災(zāi)探測(cè)特征組合實(shí)驗(yàn)的方式對(duì)比,該模型可以采用有限的實(shí)驗(yàn)獲得相關(guān)的組合,有效降低實(shí)驗(yàn)周期和成本。 其次,分析了不同特征提取算法對(duì)多傳感器火災(zāi)探測(cè)結(jié)果的影響,提出了一種用于產(chǎn)生多傳感器火災(zāi)探測(cè)分類器輸入的FFRD(Fuzzy Full Raw Data)特征提取算法。算法可以基于有限的實(shí)驗(yàn)結(jié)果產(chǎn)生用于神經(jīng)網(wǎng)絡(luò)等分類器的訓(xùn)練數(shù)據(jù)。采用動(dòng)態(tài)觀察窗的方式提取必要的多傳感器火災(zāi)信息,用于訓(xùn)練和火災(zāi)探測(cè)。并針對(duì)動(dòng)態(tài)觀察窗的窗長(zhǎng)、步長(zhǎng)和采樣頻率對(duì)多傳感器火災(zāi)探測(cè)結(jié)果的影響進(jìn)行了參數(shù)敏感性分析。同時(shí),分析了幾種不同神經(jīng)網(wǎng)絡(luò),包括BP、RBF、LVQ和PNN等在多傳感器火災(zāi)探測(cè)中的火災(zāi)探測(cè)錯(cuò)誤率、靈敏度、重復(fù)性等方面的性能,結(jié)果表明PNN在多傳感器火災(zāi)探測(cè)中有優(yōu)良的分類器性能。 第三,在FFRD特征提取算法和相關(guān)研究的基礎(chǔ)上提出了一個(gè)多傳感器火災(zāi)探測(cè)模型。該模型包括三個(gè)主要模塊：火災(zāi)特征選取模塊、有監(jiān)督的訓(xùn)練模塊和火災(zāi)探測(cè)模塊。在IS09705燃燒竄中開展了一系列全尺寸實(shí)驗(yàn),對(duì)模型的有效性進(jìn)行了驗(yàn)證。大量的實(shí)驗(yàn)驗(yàn)證結(jié)果表明,提出的多傳感器火災(zāi)探測(cè)模型有良好的火災(zāi)探測(cè)靈敏度和可靠性。同時(shí),該模型有良好的容錯(cuò)能力,可以有效降低采集數(shù)據(jù)局部波動(dòng)對(duì)多傳感器火災(zāi)探測(cè)結(jié)果的影響。 第四,提出了將建筑平面轉(zhuǎn)換為火災(zāi)節(jié)點(diǎn)網(wǎng)絡(luò)的算法模型。每個(gè)火災(zāi)節(jié)點(diǎn)的火災(zāi)危險(xiǎn)度等級(jí)可以代表相應(yīng)控制單元所對(duì)應(yīng)的保護(hù)區(qū)域的火災(zāi)危險(xiǎn)度狀況�；馂�(zāi)節(jié)點(diǎn)危險(xiǎn)度的確認(rèn)可以基于多傳感器火災(zāi)探測(cè)結(jié)果,計(jì)算火災(zāi)狀態(tài)修正系數(shù)、火源距離修正系數(shù)和多火災(zāi)探測(cè)點(diǎn)修正系數(shù)的組合確認(rèn)。 最后,提出了一個(gè)火災(zāi)危險(xiǎn)度分布確定系統(tǒng)的概念模型,系統(tǒng)包括火災(zāi)節(jié)點(diǎn)劃分模塊、多傳感器火災(zāi)探測(cè)模塊、火災(zāi)信息云、火災(zāi)危險(xiǎn)度模塊和火災(zāi)危險(xiǎn)度分布確定系統(tǒng)融合模塊。系統(tǒng)可用于火災(zāi)應(yīng)急管理,并且通過遠(yuǎn)程傳輸可以實(shí)現(xiàn)救援的遠(yuǎn)程指揮和消防資源優(yōu)化配置。給出了系統(tǒng)應(yīng)用中的幾種遠(yuǎn)程傳輸方式的網(wǎng)絡(luò)拓?fù)浣Y(jié)構(gòu)和程序流程。同時(shí),分析了火災(zāi)危險(xiǎn)度分布確定系統(tǒng)的潛在應(yīng)用前景。
[Abstract]:Fire is one of the major accidents in human life, which will cause great casualties and property losses to human beings. Human beings have been fighting relentlessly against fire. With the development of electronic engineering, communication technology and computer technology, human beings have been able to obtain powerful weapons to win in the fight against fire. After the distributed fire monitoring system is installed in important buildings, the fire development information can be provided to fire emergency management and fire fighting and rescue commanders in real time to take effective measures. On the one hand, the use of a single fire detection sensor only describes part of the fire development process information, so it will lead to high false alarm and false alarm. It is necessary to develop a multi-sensor technology for fire detection and monitoring. Detailed information, however, is difficult to obtain intuitive understanding of fire development by directly using a large number of raw data, and will quickly lead to information overload. Therefore, it is necessary to develop a fire monitoring system based on multi-sensor information fusion technology on the basis of existing fire detection technology.
The main purpose of this study is to develop a fire risk distribution determination system based on multi-sensor information fusion technology. The system is designed to assist fire monitoring, fire emergency management, fire rescue and fire fighting. By using information fusion technology, redundant information in the process of fire emergency management, fire rescue and fire fighting is reduced.
Firstly, a model of fire detection feature combination selection in multi-sensor fire detection is proposed. Based on the concept of mutual information in information entropy theory, the model adopts the criterion of maximum correlation and minimum redundancy to select fire detection features. The relevant combination is achieved by using limited experiments to effectively reduce the experimental cycle and cost.
Secondly, the influence of different feature extraction algorithms on the results of multi-sensor fire detection is analyzed, and a feature extraction algorithm based on FFRD (Fuzzy Full Raw Data) is proposed to generate the input of multi-sensor fire detection classifier. The observation window is used to extract the necessary multi-sensor fire information for training and fire detection. Parameter sensitivity analysis is carried out to study the effect of window length, step size and sampling frequency on multi-sensor fire detection results. At the same time, several different neural networks, including BP, RBF, LVQ and PNN, are analyzed. The results show that PNN has excellent classifier performance in multi-sensor fire detection.
Thirdly, a multi-sensor fire detection model is proposed based on FFRD feature extraction algorithm and related research. The model consists of three main modules: fire feature selection module, supervised training module and fire detection module. A large number of experimental results show that the proposed multi-sensor fire detection model has good sensitivity and reliability. At the same time, the model has a good fault-tolerant ability, which can effectively reduce the impact of local fluctuation of the collected data on the results of multi-sensor fire detection.
Fourthly, an algorithm model is proposed to transform the building plane into a fire node network. The fire risk level of each fire node can represent the fire risk status of the corresponding control unit in the protected area. Combination confirmation of fire source distance correction coefficient and multiple fire detection points correction coefficient.
Finally, a conceptual model of a fire risk distribution determination system is proposed, which includes a fire node partition module, a multi-sensor fire detection module, a fire information cloud, a fire risk module and a fire risk distribution determination system fusion module. The network topology and program flow of several remote transmission modes in the application of the system are given, and the potential application prospect of the fire risk distribution determination system is analyzed.
【學(xué)位授予單位】：中國(guó)科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2013
【分類號(hào)】：X932

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 崔莉,鞠海玲,苗勇,李天璞,劉巍,趙澤;無線傳感器網(wǎng)絡(luò)研究進(jìn)展[J];計(jì)算機(jī)研究與發(fā)展;2005年01期

2 姚偉祥,吳龍標(biāo),盧結(jié)成,范維澄;Method of fuzzy neural network for fire detection[J];Progress in Natural Science;1999年08期

，

本文編號(hào)：2249056