基于Elman神经网络的路面附着系数识别
作者:
基金项目:

国家自然科学基金资助项目(51705035)。


Identification of road friction coefficient based on Elman neural network
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [19]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    准确、高效地识别路面附着系数为汽车主动安全系统提供了重要输入参数。笔者提出了基于Elman神经网络识别路面附着系数方法,采用Carsim/Simulink联合仿真,获取了某车辆的63个行驶工况,共20个重要动力学响应。构建了Elman神经网络的路面附着系数识别模型,对附着系数为0.2~0.9的路面进行了识别,识别平均绝对百分比误差为4.92%,准确率为91.22%。相对于传统的BP神经网络方法,该方法使路面附着系数的识别平均绝对百分比误差降低了2.24%,准确率提升了9.82%,并且在潮湿沥青路面以及干燥沥青路面进行了实车实验,验证了该方法的有效性、可行性。

    Abstract:

    Accurate and efficient identification of road adhesion coefficient provides important input parameters for active safety system. In this paper, an identification method of road friction coefficient based on Elman neural network was proposed. Through Carsim/Simulink co-simulation, 63 driving conditions and 20 important dynamics responses of a vehicle were obtained. The identification model of road friction coefficient based on Elman neural network was constructed. The road surface with friction coefficient from 0.2 to 0.9 was identified. The average absolute percentage error was 4.92% and the accuracy was 91.22%. Compared with traditional BP neural network method, this method reduced the average absolute percentage error of road friction coefficient by 2.24% and improved the accuracy by 9.82%. Vehicle experiments on wet and dry asphalt pavement verified the effectiveness and feasibility of the proposed method.

    参考文献
    [1] 付翔, 孙威, 黄斌, 等. 基于指数加权衰减记忆无迹卡尔曼滤波的路面附着系数估计. 汽车技术, 2018(1):31-37.Fu X, Sun W, Huang B, et al. Estimation of road adhesion coefficient based on fading memory unscented Kalman filtering with exponential weighting. Automobile Technology, 2018(1):31-37.(in Chinese)
    [2] Liu Y H, Li T, Yang Y Y, et al. Estimation of tire-road friction coefficient based on combined APF-IEKF and iteration algorithm. Mechanical Systems and Signal Processing, 2017, 88:25-35.
    [3] Zhang X D, G hlich D. A hierarchical estimator development for estimation of tire-road friction coefficient. PLoS One, 2017, 12(2):e0171085.
    [4] 余卓平, 曾德全, 熊璐, 等. 基于激光雷达的无人车路面附着系数估计. 华中科技大学学报(自然科学版), 2019, 47(7):124-127.Yu Z P, Zeng D Q, Xiong L, et al. Road adhesion coefficient estimation for unmanned vehicle based on lidar. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2019, 47(7):124-127.(in Chinese)
    [5] Leng B, Jin D, Xiong L, et al. Estimation of tire-road peak adhesion coefficient for intelligent electric vehicles based on camera and tire dynamics information fusion. Mechanical Systems and Signal Processing, 2021, 150:107275.
    [6] Song S, Min K, Park J, et al. Estimating the maximum road friction coefficient with uncertainty using deep learning//2018 21st International Conference on Intelligent Transportation Systems (ITSC). New York:ACM, 2018:3156-3161.
    [7] 王岩, 梁冠群, 危银涛. 基于支持向量机的智能轮胎路面辨识算法. 汽车工程, 2020, 42(12):1671-1678, 1717.Wang Y, Liang G Q, Wei Y T. Road identification algorithm of intelligent tire based on support vector machine. Automotive Engineering, 2020, 42(12):1671-1678, 1717.(in Chinese)
    [8] Doǧan D. Road-types classification using audio signal processing and SVM method//2017 25th Signal Processing and Communications Applications Conference (SIU), May 15-18, 2017, Antalya, Turkey. IEEE, 2017:1-4.
    [9] Alonso J, López J M, Pavón I, et al. On-board wet road surface identification using tyre/road noise and Support Vector Machines. Applied Acoustics, 2014, 76:407-415.
    [10] Shao L, Jin C, Lex C, et al. Robust Road friction estimation during vehicle steering. Vehicle System Dynamics, 2019, 57(4):493-519.
    [11] Chen L, Luo Y G, Bian M Y, et al. Estimation of tire-road friction coefficient based on frequency domain data fusion. Mechanical Systems and Signal Processing, 2017, 85:177-192.
    [12] 平先尧, 李亮, 程硕, 等. 四轮独立驱动汽车多工况路面附着系数识别研究. 机械工程学报, 2019, 55(22):80-92.Ping X Y, Li L, Cheng S, et al. Tire-road friction coefficient estimators for 4WID electric vehicles on diverse road conditions. Journal of Mechanical Engineering, 2019, 55(22):80-92.(in Chinese)
    [13] 刘志强, 刘逸群. 路面附着系数的自适应衰减卡尔曼滤波估计. 中国公路学报, 2020, 33(7):176-185.Liu Z Q, Liu Y Q. Estimation algorithm for road adhesion coefficient using adaptive fading unscented Kalman filter. China Journal of Highway and Transport, 2020, 33(7):176-185.(in Chinese)
    [14] 赵治国, 朱强, 周良杰, 等. 分布式驱动HEV自适应无迹卡尔曼车速估计. 中国科学:技术科学, 2016, 46(5):481-492.Zhao Z G, Zhu Q, Zhou L J, et al. Vehicle speed estimation in driving case based on distributed self-adaptive unscented Kalman filter for 4WD hybrid electric car. Scientia Sinica (Technologica), 2016, 46(5):481-492.(in Chinese)
    [15] 熊璐, 金达, 冷搏, 等. 考虑复杂激励条件的分布式驱动电动汽车路面附着系数自适应估计方法. 机械工程学报, 2020, 56(18):123-133.Xiong L, Jin D, Leng B, et al. Adaptive tire-road friction estimation method for distributed drive electric vehicles considering multiple road excitations. Journal of Mechanical Engineering, 2020, 56(18):123-133.(in Chinese)
    [16] Feng Y C, Chen H, Zhao H Y, et al. Road tire friction coefficient estimation for four wheel drive electric vehicle based on moving optimal estimation strategy. Mechanical Systems and Signal Processing, 2020, 139:106416.
    [17] Gao L T, Xiong L, Lin X F, et al. Multi-sensor fusion road friction coefficient estimation during steering with Lyapunov method. Sensors (Basel, Switzerland), 2019, 19(18):3816.
    [18] 罗虹, 张立双, 来飞, 等. 采用横摆力矩优化分配方法的车辆稳定性控制系统. 重庆大学学报, 2010, 33(10):19-24.Luo H, Zhang L S, Lai F, et al. Vehicle stability control system design using optimal allocation of yaw moment. Journal of Chongqing University, 2010, 33(10):19-24.(in Chinese)
    [19] 汪涛. 面向商用车的路面附着系数估计研究. 重庆:重庆邮电大学, 2019. Wang T. Estimation of road adhesion coefficient for commercial vehicles. Chongqing:Chongqing University of Posts and Telecommunications, 2019. (in Chinese)
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

伍文广,张凡皓,徐孟龙.基于Elman神经网络的路面附着系数识别[J].重庆大学学报,2023,46(3):118-128.

复制
分享
文章指标
  • 点击次数:398
  • 下载次数: 960
  • HTML阅读次数: 501
  • 引用次数: 0
历史
  • 收稿日期:2021-05-24
  • 在线发布日期: 2023-03-28
文章二维码