基于NAR神經(jīng)網(wǎng)絡(luò)的車速預(yù)測及應(yīng)用
發(fā)布時(shí)間：2018-07-14 12:21
【摘要】：車速預(yù)測作為車輛智能化的重要組成部分,可為車輛的決策系統(tǒng)提供未來的行駛數(shù)據(jù),對智能車輛、安全輔助駕駛及動(dòng)力系統(tǒng)控制等研究有著重要意義。由于車速受多種因素的影響,具有顯著的時(shí)變性與非線性,所以對預(yù)測有較高的要求。本文以本車車速預(yù)測為研究對象,分析車速數(shù)據(jù)時(shí)間序列特性,利用NAR神經(jīng)網(wǎng)絡(luò)在處理非線性與時(shí)變性時(shí)間序列上的優(yōu)勢建立預(yù)測模型對車速進(jìn)行預(yù)測,并將建立的預(yù)測模型應(yīng)用于防碰撞預(yù)警系統(tǒng),對預(yù)測方法的有效性進(jìn)行驗(yàn)證。本文首先通過車載OBD-Ⅱ設(shè)備與單目視覺相機(jī)采集本車車速數(shù)據(jù)及前車距離數(shù)據(jù),并通過卡爾曼濾波對采集的數(shù)據(jù)進(jìn)行濾波,為神經(jīng)網(wǎng)絡(luò)的訓(xùn)練提供數(shù)據(jù)支持。然后,建立了基于車速自回歸的NAR網(wǎng)絡(luò)結(jié)構(gòu),并通過反向傳播算法以串聯(lián)的形式對網(wǎng)絡(luò)參數(shù)訓(xùn)練優(yōu)化,通過與HMM車速預(yù)測方法的對比以及城市公交車工況的預(yù)測分析,驗(yàn)證NAR網(wǎng)絡(luò)具有很好的預(yù)測精度、時(shí)變性能和長期預(yù)測能力。最后,將NAR神經(jīng)網(wǎng)絡(luò)預(yù)測算法應(yīng)用在防碰撞預(yù)警系統(tǒng)中,以臨界跟車安全距離模型為碰撞判斷依據(jù),預(yù)測模型預(yù)測的車速及車距用于計(jì)算臨界車距,從而將預(yù)警時(shí)間提前。試驗(yàn)結(jié)果表明NAR神經(jīng)網(wǎng)絡(luò)預(yù)測模型可對車速有效預(yù)測。
[Abstract]:Vehicle speed prediction, as an important part of vehicle intelligence, can provide future driving data for vehicle decision-making system. It is of great significance for research on intelligent vehicles, safety auxiliary driving and power system control. Because the speed is influenced by many factors, it has significant time variability and nonlinearity, so it has a higher prediction. In this paper, this paper takes the vehicle speed prediction as the research object, analyzes the characteristics of the speed data time series, and uses the NAR neural network to predict the speed of the vehicle with the advantages of the nonlinear and time-varying time series, and applies the prediction model to the anti-collision warning system, and verifies the effectiveness of the prediction method. In this paper, the vehicle speed data and the front car distance data are collected through the vehicle OBD- II equipment and the monocular vision camera, and the data are filtered through Calman filter to provide data support for the training of the neural network. Then, the NAR network structure based on auto regression is established, and the back propagation algorithm is used in series. In the form of network parameter training optimization, through comparison with the HMM speed prediction method and the prediction and analysis of urban bus conditions, it is proved that the NAR network has good prediction accuracy, time-varying performance and long-term prediction ability. Finally, the NAR neural network prediction algorithm is applied to the collision avoidance warning system, and the critical distance model of the critical car heel is used. For the basis of collision judgment, the speed and distance predicted by the model are used to calculate the critical distance, so the early warning time is advanced. The experimental results show that the NAR neural network prediction model can effectively predict the speed of the vehicle.
【學(xué)位授予單位】：大連理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：U463.6;TP183
本文編號：2121626
[Abstract]:Vehicle speed prediction, as an important part of vehicle intelligence, can provide future driving data for vehicle decision-making system. It is of great significance for research on intelligent vehicles, safety auxiliary driving and power system control. Because the speed is influenced by many factors, it has significant time variability and nonlinearity, so it has a higher prediction. In this paper, this paper takes the vehicle speed prediction as the research object, analyzes the characteristics of the speed data time series, and uses the NAR neural network to predict the speed of the vehicle with the advantages of the nonlinear and time-varying time series, and applies the prediction model to the anti-collision warning system, and verifies the effectiveness of the prediction method. In this paper, the vehicle speed data and the front car distance data are collected through the vehicle OBD- II equipment and the monocular vision camera, and the data are filtered through Calman filter to provide data support for the training of the neural network. Then, the NAR network structure based on auto regression is established, and the back propagation algorithm is used in series. In the form of network parameter training optimization, through comparison with the HMM speed prediction method and the prediction and analysis of urban bus conditions, it is proved that the NAR network has good prediction accuracy, time-varying performance and long-term prediction ability. Finally, the NAR neural network prediction algorithm is applied to the collision avoidance warning system, and the critical distance model of the critical car heel is used. For the basis of collision judgment, the speed and distance predicted by the model are used to calculate the critical distance, so the early warning time is advanced. The experimental results show that the NAR neural network prediction model can effectively predict the speed of the vehicle.
【學(xué)位授予單位】：大連理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：U463.6;TP183
【引證文獻(xiàn)】
相關(guān)期刊論文 前1條
1 魏久哲;王小勇;黃長寧;莊緒霞;;應(yīng)用NAR運(yùn)動(dòng)估計(jì)的序列幀間匹配技術(shù)[J];航天返回與遙感;2017年03期
相關(guān)碩士學(xué)位論文 前1條
1 路廣明;基于出行里程預(yù)測的插電式混合動(dòng)力汽車控制策略研究[D];吉林大學(xué);2017年
，本文編號：2121626
本文鏈接：http://sikaile.net/kejilunwen/zidonghuakongzhilunwen/2121626.html
最近更新
教材專著
