基于车辆响应的路面不平度识别方法

doi:10.13229/j.cnki.jdxbgxb20181122

摘要/Abstract

摘要：

针对路面不平度识别的问题，研究了基于车辆响应的NARX神经网络识别方法及其适用性。建立了汽车振动系统4自由度平面模型，通过仿真获得车辆响应和车轮路面不平度。对于NARX神经网络及其应用选择、输入方案优化和评价指标进行了研究，提出了车辆响应选择和组合优化的解决方案。采用NARX神经网络识别了常用的B级路面和车速为60 km/h下某轿车的前轮路面不平度，其相关系数和均方根误差分别达到96.75%和0.003 3。考虑了训练采样点数、车辆响应随机噪声、车速和路面等级的变化对训练完成的NARX神经网络效果的影响，说明了基于车辆响应识别路面不平度的NARX神经网络方法的适用性。研究结果表明，采用正交试验设计确定NARX神经网络优化输入方案和基于车辆响应识别路面不平度取得了满意的结果，两者具有良好的适用性。

关键词: 车辆工程, 路面不平度识别, 车辆响应, NARX神经网络

Abstract:

To solve the problem of road roughness identification, a NARX neural network identification method and its applicability are studied based on vehicle responses. A four degree of freedom plane model of vehicle vibration system is established, thus, the vehicle responses and road roughness of wheel can be obtained by simulation. The application selection, input scheme optimization and evaluation index of NARX neural network are studied, and the solutions of vehicle response selection and its combination optimization are put forward. The NARX neural network is used to identify the road roughness at front wheel of a car under the common road grade B and 60 km/h driving speed, for which the correlation coefficient and root mean square error are 96.75% and 0.003 3, respectively. The influences of training sampling points, vehicle response random noise, vehicle speed, and road grade on the NARX neural network are considered, and the adaptability of NARX neural network method for road roughness identification based on vehicle responses is illustrated. The results show that the use of orthogonal test design to determine the optimal input scheme of the NARX neural network and the identification of road roughness based on vehicle responses can achieve satisfactory performance and good applicability.

Key words: vehicle engineering, road roughness identification, vehicle response, NARX neural network

中图分类号:

U461.4

李杰, 郭文翠, 赵旗, 谷盛丰. 基于车辆响应的路面不平度识别方法[J]. 吉林大学学报(工学版), 2019, 49(6): 1810-1817.

Jie LI, Wen-cui GUO, Qi ZHAO, Sheng-feng GU. Road roughness identification based on vehicle responses[J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(6): 1810-1817.

图/表 8

图1

图2

表1

图3

表2

表3

表4

表5

参考文献

1	段虎明, 石峰, 谢飞, 等 . 路面不平度研究综述[J]. 振动与冲击, 2009, 28(9): 95-101.
1	Duan Hu-ming , Shi Feng , Xie Fei , et al . A survey of road roughness study[J]. Journal of Vibration and Shock, 2009, 28(9): 95-101.
2	Hammond D S , Chapman L , Thornes J E . Roughness length estimation along road transects using airborne LIDAR data[J]. Meteorological Applications, 2012, 19(4): 420-426.
3	Chen W X , Ni Z B , Hu X H . Research on pavement roughness based on the laser triangulation[J]. Photonic Sensors, 2016, 6(2): 177-180.
4	张丽霞, 赵又群, 徐培民, 等 . 路面功率谱密度识别的仿真[J]. 农业机械学报, 2007, 38(5): 15-18.
4	Zhang Li-xia , Zhao You-qun , Xu Pei-min , et al ．Simulation of road surface power spectrum density identif ication[J]. Transactions of the Chinese Society for Agricultural Machinery, 2007, 38(5): 15-18.
5	Yousefzadeh M , Azadi S , Soltani A . Road profile estimation using neural network algorithm[J]. Journal of Mechanical Science and Technology, 2010, 24(3): 743-754.
6	Solhnirzaei A , Azadi S , Kazemi R . Road profile estimation using wavelet neural network and 7-DOF vehicle dynamic systems[J]. Journal of Mechanical Science and Technology, 2012, 26(10): 3029-3036.
7	Ngwangwa H M , Heyns P S , Kululanga Grant K . An overview of the neural network based technique for monitoring of road condition via reconstructed road profiler[C]∥Southern African Transport Conference, Pretoria, Southern African, 2008: 312-329.
8	Ngwangwa H M , Heyns P S , Labuschagne F J J . Reconstruction of road defects and road roughness classification using vehicle responses with artificial neural networks simulation[J]. Journal of Terramechanics, 2010, 47(2): 97-111.
9	Ngwangwa H M , Heyns P S , Breytenbach H G A . Reconstruction of road defects and road roughness classification using artificial neural networks simulation and vehicle dynamic response: application to experimental data[J]. Journal of Terramechanics, 2014, 53(1): 1-18.
10	李杰, 高雄, 王维, 等 . 基于UniTire模型的平顺性和操纵稳定性协同研究[J]. 汽车工程, 2018, 40(2): 127-132.
10	Li Jie , Gao Xiong , Wang Wei , et al . A collaborative study on ride comfort and handling stability based on UniTire models[J]. Automotive Engineering, 2018, 40(2): 127-132.
11	周瑜 . 某轿车车身姿态半主动悬架最优控制研究[D]. 长春: 吉林大学汽车工程学院, 2016.
11	Zhou Yu . Research on the body attitude control of semi-active suspension vehicle using optimal control theory[D]. Changchun: College of Automotive Engineering, Jilin University, 2016.
12	Lei J , Yu W , Zhu X H . A novel vehicle dynamics identification method utilizing MIMU sensors based on support vector machine[C]∥10th International Conference on Sensing Technology, Nanjing, China, 2016:1-8.
13	张金 . 基于ARM的车辆姿态测量系统设计[D]. 北京: 北京交通大学电子信息工程学院, 2008.
13	Zhang Jin . Design and realization of vehicle attitude measurement system based on ARM[D]. Beijing: College of Electronic Information Engineering, Beijing Jiaotong University, 2008.
14	Andersson U , Bortolin G , Backen S , et al . Estimation of sideslip angles of a Volvo A25E articulated all-wheel drive hauler based on GPS/INS measurements[J]. SAE Technical Papers, 2011-01-2156.
15	王朝斌, 吴旭, 熊吉 . 汽车车轮轮心与车身相对位移测量方法的探讨[J]. 汽车科技, 2014(5): 41-44.
15	Wang Chao-bin , Wu Xu , Xiong Ji . Study on test method about measuring the relative displacement of body at wheel center[J]．Automobile Science and Technology, 2014(5): 41-44.
16	王小川, 史峰, 郁磊 . MATLAB神经网络43个案例分析[M]. 北京: 北京航空航天大学出版社, 2013.
17	任露泉 . 试验优化设计与分析[M]. 北京: 高等教育出版社, 2003.
18	张敏, 袁辉 . 关于标准误差应用问题的讨论[J]. 郑州工业大学学报, 1996, 17(3): 95-100.
18	Zhang Min , Yuan Hui . Discussion of application problems about standard error[J]. Journal of Zhengzhou University of Technology, 1996, 17(3): 95-100.
19	杨彦荣, 戴云 . 基于均方根误差和相关系数评价人眼像差对视网膜像质的影响[J]. 光学学报, 2017, 37(3): 389-395.
19	Yang Yan-rong , Dai Yun . Evaluation og the effect on eye aberration on retinal imaging quality based on the root mean sqaure error and correlation coefficient[J]. Acta Optica Sinica, 2017, 37(3): 389-395.
20	余志生．汽车理论[M]．北京：机械工业出版社，2009.
21	GB/T 4970—2009．汽车平顺性试验方法[S].

相关文章 15

[1]	陈鑫,阮新建,李铭,王宁,王佳宁,潘凯旋. 基于大涡模拟的离散格式改进方法及应用[J]. 吉林大学学报(工学版), 2019, 49(6): 1756-1763.
[2]	何仁,涂琨. 基于温度补偿气隙宽度的电磁制动器[J]. 吉林大学学报(工学版), 2019, 49(6): 1777-1785.
[3]	靳立强, 田端洋, 田浩, 刘蒙蒙. 汽车电子稳定系统制动增力辅助技术[J]. 吉林大学学报(工学版), 2019, 49(6): 1764-1776.
[4]	管欣,金号,段春光,卢萍萍. 汽车行驶道路侧向坡度估计[J]. 吉林大学学报(工学版), 2019, 49(6): 1802-1809.
[5]	王杨,宋占帅,郭孔辉,庄晔. 转动惯量试验台的惯性参数测量[J]. 吉林大学学报(工学版), 2019, 49(6): 1795-1801.
[6]	刘巧斌,史文库,陈志勇,骆联盟,苏志勇,黄开军. 混合可靠性模型参数的核密度和引力搜索估计[J]. 吉林大学学报(工学版), 2019, 49(6): 1818-1825.
[7]	庄蔚敏,刘洋,王鹏跃,施宏达,徐纪栓. 钢铝异质自冲铆接头剥离失效仿真[J]. 吉林大学学报(工学版), 2019, 49(6): 1826-1835.
[8]	陈百超,邹猛,党兆龙,黄晗,贾阳,石睿杨,李建桥. CE-3月球车筛网轮月面沉陷行为试验[J]. 吉林大学学报(工学版), 2019, 49(6): 1836-1843.
[9]	马芳武,倪利伟,吴量,聂家弘,徐广健. 轮腿式全地形移动机器人位姿闭环控制[J]. 吉林大学学报(工学版), 2019, 49(6): 1745-1755.
[10]	马芳武,韩露,周阳,王世英,蒲永锋. 采用聚乳酸复合材料的汽车零件多材料优化设计[J]. 吉林大学学报(工学版), 2019, 49(5): 1385-1391.
[11]	高振海,孙天骏,何磊. 汽车纵向自动驾驶的因果推理型决策[J]. 吉林大学学报(工学版), 2019, 49(5): 1392-1404.
[12]	张博,张建伟,郭孔辉,丁海涛,褚洪庆. 路感模拟用永磁同步电机电流控制[J]. 吉林大学学报(工学版), 2019, 49(5): 1405-1413.
[13]	王鹏宇,赵世杰,马天飞,熊晓勇,程馨. 基于联合概率数据关联的车用多传感器目标跟踪融合算法[J]. 吉林大学学报(工学版), 2019, 49(5): 1420-1427.
[14]	胡兴军,惠政,郭鹏,张扬辉,张靖龙,王靖宇,刘飞. 基于流固耦合的汽车气动特性[J]. 吉林大学学报(工学版), 2019, 49(5): 1414-1419.
[15]	韩小健,赵伟强,陈立军,郑宏宇,刘阳,宗长富. 基于区域采样随机树的客车局部路径规划算法[J]. 吉林大学学报(工学版), 2019, 49(5): 1428-1440.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

方案	R/%	RMSE	方案	R/%	RMSE
1	0.00	0.015 00	17	96.29	0.003 48
2	26.47	0.013 40	18	95.05	0.004 38
3	16.72	0.013 52	19	93.06	0.004 66
4	36.87	0.012 22	20	96.21	0.003 54
5	29.07	0.013 50	21	92.85	0.004 84
6	43.41	0.014 30	22	91.18	0.006 00
7	43.36	0.012 38	23	94.93	0.003 76
8	32.84	0.014 28	24	84.89	0.005 98
9	75.44	0.008 96	25	42.26	0.013 62
10	93.43	0.004 50	26	32.13	0.015 26
11	72.52	0.008 94	27	48.30	0.014 24
12	93.59	0.004 44	28	47.91	0.012 02
13	94.39	0.004 26	29	19.28	0.015 32
14	94.51	0.004 38	30	21.52	0.015 42
15	95.44	0.003 70	31	36.46	0.013 44
16	96.35	0.003 30	32	28.76	0.014 38

采样点数	R/%	RMSE
216	38.75	0.012 0
240	58.69	0.012 3
270	65.46	0.012 1
310	83.93	0.007 0
360	83.39	0.006 8
432	91.33	0.006 6
540	93.17	0.005 9
720	93.29	0.006 0
1080	93.56	0.005 0

信噪比/dB	R/%	RMSE
1	68.10	0.013 2
3	77.97	0.008 0
5	84.47	0.007 5
10	87.82	0.006 7
20	92.71	0.004 6

车速/(km·h^-1)	R/%	RMSE
40	89.66	0.005 6
50	96.94	0.002 9
60	95.25	0.003 7
70	96.18	0.003 1
80	89.56	0.004 4

路面等级	R/%	RMSE
A级	92.26	0.005 6
B级	94.70	0.005 0
C级	85.02	0.014 6
D级	62.06	0.036 8