【摘要】：近年來,隨著汽車工業(yè)和道路交通的快速發(fā)展,汽車側(cè)翻事故成為受到人們更多關(guān)注的重要安全問題。車輛在高速行駛并進行緊急轉(zhuǎn)向時,在較短的時間內(nèi)容易發(fā)生側(cè)翻,因此車輛的側(cè)翻預(yù)警變得尤為重要。本文主要對SUV車輛發(fā)生的非絆倒型側(cè)翻進行研究,使用隱形馬爾可夫模型(HMM)進行側(cè)翻預(yù)警,可以實時的對車輛的運動狀態(tài)進行監(jiān)測和預(yù)測,并提前發(fā)出警示,從而提高了車輛行駛的安全性。首先采用Carsim軟件在階躍轉(zhuǎn)向、斜坡轉(zhuǎn)向、雙移線轉(zhuǎn)向、魚鉤轉(zhuǎn)向四種容易發(fā)生側(cè)翻的工況下進行仿真,得到HMM模型的可觀察序列:側(cè)傾角、側(cè)向加速度。對采集的數(shù)據(jù)進行預(yù)處理,根據(jù)車輛的運動狀態(tài):直線運動、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)分類并分割,使用K-means算法確定了運動狀態(tài)的界限值,作為文中模型訓(xùn)練和辨識的前提。其次建立了HMM的雙層運動狀態(tài)模型,模型的底層為多維的車輛運動參數(shù),模型的高層對應(yīng)著運動狀態(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,對復(fù)合工況下采集的數(shù)據(jù)進行辨識,辨別出車輛當前所處的運動狀態(tài)。同時運用馬爾可夫預(yù)測法,對車輛未來3s內(nèi)將要發(fā)生的運動狀態(tài)進行預(yù)測,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)進行預(yù)測。最后將人工神經(jīng)網(wǎng)絡(luò)(ANN)與HMM模型相結(jié)合,以HMM當前用于辨識車輛行駛狀態(tài)的運動參數(shù)數(shù)值作為ANN模型的輸入,并對ANN模型進行訓(xùn)練,選用的BP-神經(jīng)網(wǎng)絡(luò)算法對車輛下一時間段的三個運動參數(shù)側(cè)傾角、側(cè)向加速度以及方向盤轉(zhuǎn)角的數(shù)值進行預(yù)測。HMM模型實現(xiàn)了對車輛下一時間段的運動狀態(tài)進行預(yù)測,而ANN實現(xiàn)了對車輛下一時間段的參數(shù)數(shù)據(jù)值進行預(yù)測,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輛將要發(fā)生側(cè)翻的危險程度。
[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)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：U461.6

【參考文獻】

相關(guān)期刊論文 前9條

1 郁偉煒;吳卿;;基于HMM的駕駛員疲勞識別在智能汽車空間的應(yīng)用[J];計算機應(yīng)用與軟件;2011年10期

2 朱穎;周煒;郭志平;李文亮;張學(xué)文;;基于車輛側(cè)傾角側(cè)翻預(yù)警算法的研究[J];機械設(shè)計與制造;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行為辨識與分析[J];汽車工程;2010年07期

4 王健;余貴珍;張為;丁能根;;基于滑模觀測和模糊推理的車輛側(cè)翻實時預(yù)警技術(shù)[J];農(nóng)業(yè)機械學(xué)報;2010年06期

5 陳君毅;王宏雁;郁佳文;;道路交通安全現(xiàn)代化水平綜合評價模型[J];同濟大學(xué)學(xué)報(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;2009年04期

7 宗長富;楊肖;王暢;張廣才;;汽車轉(zhuǎn)向時駕駛員駕駛意圖辨識與行為預(yù)測[J];吉林大學(xué)學(xué)報(工學(xué)版);2009年S1期

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

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

，

本文編號：2179100