Abstract：In this paper, the method of road grade identification based on the vehicle vibration response reverse analysis is proposed. First, the quarter vehicle model and road model are built up, and the vehicle vibration response simulation data under different random input road are decomposed by Hilbert-Huang transform. Then, the Instantaneous energy are obtained and the corresponding feature parameters are extracted. The feature parameters are used as the input of the probabilistic neural network to complete the design of road classifier. Finally, the acceleration sensors are used to collect the vibration response data on typical road surface. The experimental data is also analyzed using the Hilbert-Huang transform and the corresponding feature parameters are extracted and inputted into the trained probabilistic neural network classifier to obtain the road grade identification result of the experimental road. The results show that the vehicle vibration response inverse analysis that combining with Hilbert Huang transform and probabilistic neural network can realize the identification of the road grade.
陈双，王丽佳. 基于车辆振动响应反向分析的路面等级辨识方法[J]. 振动与冲击, 2022, 41(17): 145-151.
CHEN Shuang, WANG Lijia. Pavement grade identification method based on reverse analysis of vehicle vibration response. JOURNAL OF VIBRATION AND SHOCK, 2022, 41(17): 145-151.
[1] 谷盛丰. 基于车辆响应识别路面不平度的神经网络方法研究[D]. 长春:吉林大学, 2018.
GU Sheng-feng. Research on Neural Network Method for Recognizing Road Surface Roughness Based on Vehicle Response[D]. Changchun: Jilin University, 2018.
[2] Chen H T, Lai C Y, Hsu C C, et al. Vision-Based Road Bump Detection Using a Front-Mounted Car Camcorder[C]. Pattern Recognition(ICPR), 2014 22nd International Conference on. IEEE, 2014: 4537-4542.
[3] Vidas Žuraulis, Vytenis Surblys. Technological measures of forefront road identification for vehicle comfort and safety improvement[J]. Transport, 2019, 34(3): 363-372.
[4] Nicholas Dembski, G Rizzoni, A S oliman. An improved design of a vehicle based off-Road terrain profile measurement system[C]. Commercial Vehicle Engineering Congress&Exhibition, 2018.
[5] 刘汉儒. 基于激光雷达的智能汽车前方不平路面识别方法[D]. 哈尔滨：哈尔滨工业大学, 2019.
LIU Han-ru. Lidar Based Recognition of Uneven Road Surface in Front of Intelligent Vehicle[D]. Harbin: Harbin Institute of Technology, 2019.
[6] 许华伟. 基于毫米波雷达时频特征的路面动目标识别[D]. 厦门: 厦门大学, 2019.
XU Hua-wei. Recognition of Road Moving Target Based on The Time-Frequency Characteristics of Millimeter Wave Radar[D]. Xiamen: Xiamen University, 2019.
[7] 李以磊. 基于激光雷达的车前地形高程信息测量技术研究[D]. 长春:吉林大学, 2018.
LI Yi-lei. Research on Measurement Technique of Road Elevation Information Front of Vehicle Based on 3D-Laser Radar[D]. Changchun: Jilin University, 2018.
[8] Wang Z F, Dong M, Qin Y, et al. Suspension system state estimation using adaptive Kalman filtering based on road classification[J]. Vehicle System Dynamics, 2017, 55(3):371-389.
[9] Nguyen T H, Nguyen T L, Sidorov D N, et al. Machine learning algorithms application to road defects classification[J]. Intelligent Decision Technologies, 2018(11):59-66.
[10] Qin Y, Dong M, Zhao F, et al. Road profile classification for vehicle semi-active suspension system based on adaptive neuro-fuzzy inference system[C]. 2015 54th IEEE Conference oh Decision and Control (CDC). IEEE, 2015:1533-1538.
[11] 张丽霞.高速公路路面不平度识别研究[J]. 结构工程师,2014, 30(4): 105-111.
ZHANG Li-xia. Study on Road Surface Roughness Identification of Free-ways[J]. Structural Engineers， 2014, 30(4): 105-111.
[12] 秦也辰.基于路面识别的车辆半主动悬架控制研究[D]. 北京: 北京理工大学,2016.
QIN Ye-chen. Research on Vehicle Semi-Active Suspension System Based on Road Estimation[D]. Beijing: Beijing Institute of Technology, 2016.
[13] 王静, 鲁杨等. 基于改进AFSA的路面不平度时域估测[J]. 安徽农业大赞学报, 2017, 44(1): 153-157.
Wang Jing, Lu Yang, et al. Time Domain Estimation of Road Roughness with Improved AFSA [J]. Journal of Anhui Agricultural University, 2017,44(1) : 153-157．
[14] 张义平. 爆破振动信号的HHT分析与应用研究[D]. 长沙: 中南大学, 2006.
ZHANG Yi-ping. HHT Analysis and Application Research of Blasting Vibration Signal[D]. Changsha: Central South University, 2016.
[15] 冯红武, 王建昌. 希尔伯特-黄变换在地震信号时频分析中的应用研究[J]. 高原地震, 2018, 30(04): 11-15.
FENG Hong-wu, WANG Jian-chang. Applied research on Hilbert-Huang transform in time-frequency analysis of seismic signal[J]. Plateau Earthquake Research, 2018, 30(04): 11-15.
[16] 孟宗, 胡猛, 谷伟明, 赵东方. 基于LMD多尺度熵和概率神经网络的滚动轴承故障诊断方法[J]. 中国机械工程, 2016, 27(04): 433-437.
MENG Zong, HU Meng, GU Wei-ming, ZHAO Dong-fang. Rolling Bearing Fault Diagnosis Method Based on LMD Multi-scale Entropy and Probabilistic Neural Network[J]. China Mechanical Engineering, 2016, 27(04): 433-437.
[17] 邱尚龙. 基于HHT与PNN的输电线路故障辨识方法研究[D]. 阜新: 辽宁工程技术大学, 2018.
QIU Shang-long. Transmission Line Faults Identification Method Based on HHT and PNN[D]. Fuxin: Liaoning Technical University, 2018.
[18] 喻凡, 林逸. 汽车系统动力学(第2版)[M]. 北京: 机械工业出版社, 2017.
YU Fan, LIN Yi. Automobile System Dynamics(2nd Edition) [M]. Beijing: China Machine Press, 2017.
