【摘要】：近年來(lái),隨著汽車(chē)工業(yè)和道路交通的快速發(fā)展,汽車(chē)側(cè)翻事故成為受到人們更多關(guān)注的重要安全問(wèn)題。車(chē)輛在高速行駛并進(jìn)行緊急轉(zhuǎn)向時(shí),在較短的時(shí)間內(nèi)容易發(fā)生側(cè)翻,因此車(chē)輛的側(cè)翻預(yù)警變得尤為重要。本文主要對(duì)SUV車(chē)輛發(fā)生的非絆倒型側(cè)翻進(jìn)行研究,使用隱形馬爾可夫模型(HMM)進(jìn)行側(cè)翻預(yù)警,可以實(shí)時(shí)的對(duì)車(chē)輛的運(yùn)動(dòng)狀態(tài)進(jìn)行監(jiān)測(cè)和預(yù)測(cè),并提前發(fā)出警示,從而提高了車(chē)輛行駛的安全性。首先采用Carsim軟件在階躍轉(zhuǎn)向、斜坡轉(zhuǎn)向、雙移線轉(zhuǎn)向、魚(yú)鉤轉(zhuǎn)向四種容易發(fā)生側(cè)翻的工況下進(jìn)行仿真,得到HMM模型的可觀察序列:側(cè)傾角、側(cè)向加速度。對(duì)采集的數(shù)據(jù)進(jìn)行預(yù)處理,根據(jù)車(chē)輛的運(yùn)動(dòng)狀態(tài):直線運(yùn)動(dòng)、正常轉(zhuǎn)向、緊急轉(zhuǎn)向、側(cè)翻狀態(tài),將四種工況下的數(shù)據(jù)分類(lèi)并分割,使用K-means算法確定了運(yùn)動(dòng)狀態(tài)的界限值,作為文中模型訓(xùn)練和辨識(shí)的前提。其次建立了HMM的雙層運(yùn)動(dòng)狀態(tài)模型,模型的底層為多維的車(chē)輛運(yùn)動(dòng)參數(shù),模型的高層對(duì)應(yīng)著運(yùn)動(dòng)狀態(tài)的多維高斯隱馬可夫模型(MGHMM)。并采用Baum-Welch算法訓(xùn)練模型,對(duì)復(fù)合工況下采集的數(shù)據(jù)進(jìn)行辨識(shí),辨別出車(chē)輛當(dāng)前所處的運(yùn)動(dòng)狀態(tài)。同時(shí)運(yùn)用馬爾可夫預(yù)測(cè)法,對(duì)車(chē)輛未來(lái)3s內(nèi)將要發(fā)生的運(yùn)動(dòng)狀態(tài)進(jìn)行預(yù)測(cè),若發(fā)生側(cè)翻則觸發(fā)預(yù)警裝置,不發(fā)生側(cè)翻則循環(huán)進(jìn)行預(yù)測(cè)。最后將人工神經(jīng)網(wǎng)絡(luò)(ANN)與HMM模型相結(jié)合,以HMM當(dāng)前用于辨識(shí)車(chē)輛行駛狀態(tài)的運(yùn)動(dòng)參數(shù)數(shù)值作為ANN模型的輸入,并對(duì)ANN模型進(jìn)行訓(xùn)練,選用的BP-神經(jīng)網(wǎng)絡(luò)算法對(duì)車(chē)輛下一時(shí)間段的三個(gè)運(yùn)動(dòng)參數(shù)側(cè)傾角、側(cè)向加速度以及方向盤(pán)轉(zhuǎn)角的數(shù)值進(jìn)行預(yù)測(cè)。HMM模型實(shí)現(xiàn)了對(duì)車(chē)輛下一時(shí)間段的運(yùn)動(dòng)狀態(tài)進(jìn)行預(yù)測(cè),而ANN實(shí)現(xiàn)了對(duì)車(chē)輛下一時(shí)間段的參數(shù)數(shù)據(jù)值進(jìn)行預(yù)測(cè),兩者結(jié)合,可以使得駕駛員能夠更加直觀和具體地判定車(chē)輛將要發(fā)生側(cè)翻的危險(xiǎn)程度。
[Abstract]:In recent years, with the rapid development of automotive industry and road traffic, vehicle rollover accidents have become an important safety issue that attracts more and more attention. Vehicles are prone to rollover in a relatively short period of time when they are driving at high speed and making emergency steering. Therefore, vehicle rollover warning becomes particularly important. The tripping rollover is studied. The hidden Markov model (HMM) is used for rollover warning, which can monitor and predict the vehicle's movement state in real time and give warning in advance, so as to improve the vehicle's driving safety. The observable sequence of HMM model is obtained by simulation under the condition of rollover: rollover angle and lateral acceleration. The collected data are pre-processed and classified according to the motion state of vehicle: linear motion, normal steering, emergency steering and rollover. The motion state is determined by K-means algorithm. Secondly, a two-layer motion state model of HMM is established. The bottom layer of the model is multi-dimensional vehicle motion parameters, and the upper layer of the model corresponds to the multi-dimensional Gaussian Hidden Markov Model (MGHMM) of the motion state. At the same time, Markov prediction method is used to predict the motion state of the vehicle in the next three seconds. If rollover occurs, the warning device will be triggered and the cycle will be forecasted. Finally, the artificial neural network (ANN) is combined with the HMM model to identify the vehicle at present. The motion parameters of the vehicle running state are taken as the input of ANN model, and the ANN model is trained. The BP-neural network algorithm is selected to predict the roll angle, lateral acceleration and steering angle of the three motion parameters in the next period of time. The HMM model realizes the prediction of the vehicle moving state in the next period of time. The combination of ANN and ANN can make the driver more intuitive and specific to determine the danger degree of vehicle rollover.
【學(xué)位授予單位】：南京林業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類(lèi)號(hào)】：U461.6

【參考文獻(xiàn)】

相關(guān)期刊論文 前9條

1 郁偉煒;吳卿;;基于HMM的駕駛員疲勞識(shí)別在智能汽車(chē)空間的應(yīng)用[J];計(jì)算機(jī)應(yīng)用與軟件;2011年10期

2 朱穎;周煒;郭志平;李文亮;張學(xué)文;;基于車(chē)輛側(cè)傾角側(cè)翻預(yù)警算法的研究[J];機(jī)械設(shè)計(jì)與制造;2011年02期

3 呂岸;胡振程;陳慧;;基于高斯混合隱馬爾科夫模型的高速公路超車(chē)行為辨識(shí)與分析[J];汽車(chē)工程;2010年07期

4 王健;余貴珍;張為;丁能根;;基于滑模觀測(cè)和模糊推理的車(chē)輛側(cè)翻實(shí)時(shí)預(yù)警技術(shù)[J];農(nóng)業(yè)機(jī)械學(xué)報(bào);2010年06期

5 陳君毅;王宏雁;郁佳文;;道路交通安全現(xiàn)代化水平綜合評(píng)價(jià)模型[J];同濟(jì)大學(xué)學(xué)報(bào)(自然科學(xué)版);2010年01期

6 王志堂;蔡淋波;;隱馬爾可夫模型(HMM)及其應(yīng)用[J];湖南科技學(xué)院學(xué)報(bào);2009年04期

7 宗長(zhǎng)富;楊肖;王暢;張廣才;;汽車(chē)轉(zhuǎn)向時(shí)駕駛員駕駛意圖辨識(shí)與行為預(yù)測(cè)[J];吉林大學(xué)學(xué)報(bào)(工學(xué)版);2009年S1期

8 何毅;楊新;;基于隱馬爾科夫度量場(chǎng)模型的車(chē)輛檢測(cè)和跟蹤[J];上海交通大學(xué)學(xué)報(bào);2008年02期

9 郭孔輝,軋浩;車(chē)輛四輪轉(zhuǎn)向系統(tǒng)的控制方法[J];吉林工業(yè)大學(xué)學(xué)報(bào);1998年04期

，

本文編號(hào)：2179100