本文選題：風(fēng)險(xiǎn)預(yù)警　切入點(diǎn)：預(yù)警指標(biāo)　出處：《中國(guó)安全科學(xué)學(xué)報(bào)》2017年08期

【摘要】：為更有效地實(shí)現(xiàn)具有復(fù)雜性、時(shí)變性及非線性的機(jī)場(chǎng)滑行道安全風(fēng)險(xiǎn)預(yù)警,降低事故發(fā)生率,針對(duì)小波神經(jīng)網(wǎng)絡(luò)(WNN)訓(xùn)練過(guò)程易陷入局部最優(yōu)以及訓(xùn)練不穩(wěn)定等影響預(yù)測(cè)準(zhǔn)確性問題,采用蝙蝠算法(BA)優(yōu)化WNN,設(shè)計(jì)和實(shí)現(xiàn)基于BA-WNN的滑行道安全風(fēng)險(xiǎn)預(yù)警方法,并將其與BP神經(jīng)網(wǎng)絡(luò)(BPNN)、WNN、遺傳算法優(yōu)化小波網(wǎng)絡(luò)(GA-WNN)等3種方法進(jìn)行有效性對(duì)比。結(jié)果表明:BA-WNN方法的預(yù)警準(zhǔn)確率最高(約為84%),在所有工況下誤警率都較低。
[Abstract]:In order to realize more effectively the safety risk early warning of airport taxiway with complexity, time-varying and nonlinear, and reduce the incidence of accidents, Aiming at the problem that the training process of wavelet neural network (WNN) is prone to fall into the local optimum and the training is unstable, the bat algorithm is used to optimize the WNNs, and the method of taxiway safety risk warning based on BA-WNN is designed and implemented. It is compared with BP neural network BPNN and genetic algorithm optimization wavelet network GA-WNN. The results show that the WA-WNN method has the highest early warning accuracy (about 84%), and the false alarm rate is low under all working conditions.
【作者單位】： 武漢理工大學(xué)計(jì)算機(jī)科學(xué)與技術(shù)學(xué)院;武漢理工大學(xué)交通物聯(lián)網(wǎng)技術(shù)湖北省重點(diǎn)實(shí)驗(yàn)室;武漢理工大學(xué)管理學(xué)院;
【基金】：國(guó)家自然科學(xué)基金資助(71271163)
【分類號(hào)】：V328;V351.11
，

本文編號(hào)：1654689