王娟 朱亞男
摘要:精確可靠的列車(chē)制動(dòng)預(yù)測(cè)模型對(duì)于列車(chē)制動(dòng)控制系統(tǒng)和列車(chē)精確停車(chē)控制等應(yīng)用領(lǐng)域意義重大,由于列車(chē)制動(dòng)過(guò)程受線路條件、車(chē)型自身參數(shù)及外界天氣環(huán)境等客觀因素影響,是一個(gè)復(fù)雜的非線性系統(tǒng),因此采用免疫RBF神經(jīng)網(wǎng)絡(luò)逼近制動(dòng)系統(tǒng)模型。本文介紹了免疫RBF網(wǎng)絡(luò)拓?fù)浣Y(jié)構(gòu)的構(gòu)建方法,分析了列車(chē)制動(dòng)過(guò)程模型,建立了列車(chē)制停的免疫RBF網(wǎng)絡(luò),并提取實(shí)車(chē)運(yùn)行數(shù)據(jù)進(jìn)行特征化處理后訓(xùn)練網(wǎng)絡(luò)從而實(shí)現(xiàn)了列車(chē)制動(dòng)的精準(zhǔn)預(yù)測(cè)。經(jīng)實(shí)車(chē)數(shù)據(jù)仿真實(shí)驗(yàn)驗(yàn)證,本文建立的列車(chē)制停免疫RBF網(wǎng)絡(luò)性能優(yōu)越,預(yù)測(cè)停車(chē)位置與實(shí)際值吻合率高達(dá)96.3%,具有較大應(yīng)用價(jià)值。
關(guān)鍵詞:人工免疫系統(tǒng);RBF網(wǎng)絡(luò);列車(chē)制動(dòng)
中圖分類(lèi)號(hào):TP301.6文獻(xiàn)標(biāo)識(shí)碼:A
Abstract:Accurate and reliable train braking prediction models are of great significance to application fields such as train braking control systems and train accurate parking control.Because the train braking process is affected by objective factors such as line conditions,vehicle model parameters,and external weather conditions,it is a complex Nonlinear system,therefore,an immune RBF neural network is used to approximate the braking system model.This article introduces the construction method of the immune RBF network topology,analyzes the train braking process model,establishes the immune RBF network for train stopping,and extracts the actual train operation data for characterization and then trains the network to realize the train braking precise prediction.The actual vehicle data simulation experiment verifies that the trainstop immune RBF network established in this paper has superior performance,and the predicted parking position coincides with the actual value as high as 96.3%,which has great application value.
Key words:artificial immune system;RBF network;train braking
制動(dòng)系統(tǒng)是鐵道機(jī)車(chē)車(chē)輛的重要組成部分,研究制動(dòng)系統(tǒng)提高制動(dòng)性能對(duì)鐵路行車(chē)安全意義重大。列車(chē)制動(dòng)時(shí),是由司機(jī)操縱本務(wù)機(jī)車(chē)向其他機(jī)車(chē)及車(chē)輛發(fā)送制動(dòng)命令及風(fēng)缸風(fēng)壓等信息,各車(chē)輛接到命令后,再通過(guò)各自空氣制動(dòng)系統(tǒng)協(xié)同動(dòng)作,共同實(shí)施制動(dòng),所以列車(chē)最終制停后的停車(chē)位置與司機(jī)的操作水平直接相關(guān)。隨著列車(chē)速度的增加,我們對(duì)精確停車(chē)的要求也不斷增加,恰逢信息技術(shù)快速發(fā)展,智能駕駛逐漸成為鐵路運(yùn)維方式的全新發(fā)展方向,也就是說(shuō),在未來(lái),不再依賴人工而是借助智能模型實(shí)現(xiàn)全自動(dòng)的精確停車(chē)已成為必然趨勢(shì)。
因此,研究列車(chē)制動(dòng)預(yù)測(cè)模型,對(duì)于列車(chē)制動(dòng)控制系統(tǒng)及ATO列車(chē)停車(chē)控制實(shí)現(xiàn)精準(zhǔn)停車(chē)等方面都意義重大。由于列車(chē)制動(dòng)過(guò)程受線路條件、車(chē)型自身參數(shù)及外界天氣環(huán)境等客觀因素影響,是一個(gè)復(fù)雜的非線性系統(tǒng),而神經(jīng)網(wǎng)絡(luò)能夠映射高維函數(shù),非常適合應(yīng)用于制動(dòng)預(yù)測(cè)領(lǐng)域。神經(jīng)網(wǎng)絡(luò)中的徑向基函數(shù)(RadialBasis Function,RBF)神經(jīng)網(wǎng)絡(luò)(RBF網(wǎng)絡(luò))是一種典型的局部逼近網(wǎng)絡(luò)模型[1],能夠逼近任意非線性函數(shù)。文獻(xiàn)[2]作者提出了一種基于免疫機(jī)制的RBF網(wǎng)絡(luò)設(shè)計(jì)與訓(xùn)練策略,引入人工免疫系統(tǒng)特有的疫苗抽取與接種機(jī)理,從而獲得了更為優(yōu)化的網(wǎng)絡(luò)性能。本文研究列車(chē)制動(dòng)預(yù)測(cè)模型,并采用列車(chē)制動(dòng)停車(chē)前惰性階段的列車(chē)運(yùn)行數(shù)據(jù)作為訓(xùn)練數(shù)據(jù)集,借助免疫RBF網(wǎng)絡(luò)對(duì)列車(chē)精準(zhǔn)停車(chē)模型進(jìn)行訓(xùn)練,從而實(shí)現(xiàn)列車(chē)精準(zhǔn)停車(chē)。