基于车辆振动响应反向分析的路面等级辨识方法  

Pavement grade identification method based on reverse analysis of vehicle vibration response

作　　者：陈双[1] 王丽佳 CHEN Shuang;WANG Lijia(College of Automobile and Traffic Engineering,Liaoning University of Technology,Jinzhou 121000,China)

机构地区：[1]辽宁工业大学汽车与交通工程学院,辽宁锦州121000

出　　处：《振动与冲击》2022年第17期145-151,169,共8页Journal of Vibration and Shock

基　　金：国家自然基金青年基金(51605213);辽宁省高等学校创新人才支持计划。

摘　　要：提出一种利用希尔伯特黄变换和概率神经网络进行车辆振动响应反向分析的路面等级辨识方法,为主动悬架控制提供有效信息。建立车辆模型和随机输入路面模型,利用希尔伯特黄变换对不同等级路面下的车辆振动响应仿真数据进行分解变换,得到车辆振动响应的瞬时能量;提取瞬时能量的敏感特征参数,利用概率神经网络训练路面分类器,确定路面等级与特征参数范围的映射关系,完成路面等级分类器的设计;利用加速度传感器采集车辆在典型路面下的振动响应数据,提取试验数据的特征参数,并将其输入到训练完成的路面分类器中,实现试验路面等级辨识。辨识结果表明,基于车辆振动响应的反向分析法,结合希尔伯特黄变换和概率神经网络,可以实现对车辆当前行驶路面等级的辨识。Here,a pavement grade identification method based on Hilbert-Huang transformation and probabilistic neural network being used for reverse analysis of vehicle vibration response was proposed to provide effective information for active suspension control.Firstly,vehicle model and random input pavement model were established.Hilbert-Huang transformation was used to decompose and transform simulation data of vehicle vibration responses under different grades of pavements,and obtain instantaneous energy of vehicle vibration responses.Then,sensitive characteristic parameters of instantaneous energy were extracted,the probabilistic neural network was used to train pavement classifier,the mapping relation among pavement grade and ranges of characteristic parameters was determined to complete design of pavement grade classifier.Finally,acceleration sensors were used to collect vehicle vibration response data under typical road surfaces,extract characteristic parameters of test data,and input them into the trained road surface classifier for realizing grade identification of the tested road surface.The identification results showed that the reverse analysis method based on vehicle vibration response,combined with Hilbert-Huang transformation and probabilistic neural network,can identify the current vehicle driving pavement grade.

关 键 词：路面等级辨识 反向分析 希尔伯特黄变换 概率神经网络 

分 类 号：TH113[机械工程—机械设计及理论]