針對(duì)目前火災(zāi)探測(cè)技術(shù)難以滿足實(shí)際需要的問(wèn)題，在分析RBF 網(wǎng)絡(luò)結(jié)構(gòu)特點(diǎn)及最近鄰聚類學(xué)習(xí)算法的基礎(chǔ)上，提出用RBF 神經(jīng)網(wǎng)絡(luò)建立火災(zāi)探測(cè)器模型，以火災(zāi)初期實(shí)驗(yàn)得到的環(huán)境溫度、煙霧濃度、CO 含量為輸入，以明火概率、陰燃火概率、無(wú)火概率為輸出對(duì)RBF 網(wǎng)絡(luò)進(jìn)行訓(xùn)練，并進(jìn)行仿真試驗(yàn)，結(jié)果表明，實(shí)際輸出與期望輸出的相差較小。
關(guān)鍵詞：徑向基函數(shù)（RBF）；神經(jīng)網(wǎng)絡(luò)；最近鄰聚類算法；火災(zāi)探測(cè)器模型
Abstract: In view of the problem that presently, the fire detective technology difficultly meet the actual needs, and on the basis of analyzing the characteristic of RBF network structure and the Nearest Neighbor-Clustering Algorithm, there comes a proposal that to use the RBF neural network to establish fire detector model .Taking the ambient temperature, the smog density, the CO content which obtains by the experiment of fire initial period as the input, and flame probability, glowing fire probability and misfire probability as the output. Researchers carry on the training to the RBF network. Meanwhile, they carry on the simulation experiment. As a result, there is little difference between the actual output and expected output.
Key word: Radial Basis Function (RBF), Neural networks ，Nearest Neighbor-Clustering
Algorithm, Fire detector model