|
|
Variable weight PSO-Elman neural network based roadadhesion coefficient estimation |
Juncheng WANG(),Fahui WANG |
1. School of Mechanical Engineering, Zhejiang Sci-Tech University, Hangzhou 310018, China |
|
|
Abstract The variable weight particle swarm optimization (PSO)-Elman neural network was proposed for road adhesion coefficient estimation, in order to address the issue that the unstable weight update of traditional neural network leads to the poor accuracy in the estimation of road adhesion coefficient. The neural network model was constructed on the basis of a seven degrees-of-freedom vehicle dynamic model. The particle swarm algorithm was applied in the Elman neural network model to reduce the training absolute error. The linear decreasing weight strategy was used to change the weight of the particle swarm algorithm, which was useful for balancing the particle’s global and local search ability. Thus, the optimization of network weight arrays were realized. Then, the correlation curve of optimal slip ratio and rood adhesion coefficient was fitted by the Fourier approximation method. Theoretical analysis and simulation verification proved that this method can improve the estimation accuracy of road adhesion coefficient. Simulation results showed that, under both fixed and unfixed adhesion coefficient roads, the root-mean-square error of the road adhesion coefficient obtained by the proposed variable weight PSO-Elman neural network estimation method was reduced by 35.62% and 19.20% on average compared with that of the traditional Elman neural network. Furthermore, the anti-lock control effect was also effectively improved.
|
Received: 21 June 2023
Published: 05 March 2024
|
|
Fund: 国家自然科学基金资助项目(52205135). |
基于变权重PSO-Elman神经网络的路面附着系数估计
针对传统神经网络权值更新不稳定导致路面附着系数预估精度不高的问题,提出基于变权重粒子群优化(PSO)-Elman神经网络的路面附着系数估计方法. 搭建基于7自由度汽车动力学模型的神经网络模型,在Elman神经网络模型中引入粒子群算法降低训练绝对误差,并使用线性权重递减策略对粒子群算法中的权重进行改变,平衡粒子全局和局部搜索能力,实现网络权值矩阵优化;采用傅里叶函数方法拟合出理想滑移率-路面附着系数相关曲线;通过理论分析和仿真验证,证明采用该方法能够提升路面附着系数预估精度. 仿真结果表明:在定附和变附路面行驶工况下,相比于传统Elman神经网络,采用变权重PSO-Elman神经网络的路面附着系数估计方法获得的路面附着系数均方根误差分别平均降低了35.62%和19.20%,有效提升了防抱死控制效果.
关键词:
车辆状态,
路面附着系数,
神经网络,
粒子群,
防抱死控制
|
|
[1] |
《中国公路学报》编辑部 中国汽车工程学术研究综述·2017[J]. 中国公路学报, 2017, 30 (6): 1- 197 Editorial Department of China Journal of Highway and Transport Review on China’s automotive engineering research progress: 2017[J]. China Journal of Highway and Transport, 2017, 30 (6): 1- 197
doi: 10.19721/j.cnki.1001-7372.2017.06.001
|
|
|
[2] |
NGUYEN T, LECHNER B, WONG Y D Response-based methods to measure road surface irregularity: a state-of-the-art review[J]. European Transport Research Review, 2019, 11 (1): 1- 18
doi: 10.1186/s12544-018-0328-2
|
|
|
[3] |
LEE H, TAHERI S Intelligent tires: a review of tire characterization literature[J]. IEEE Intelligent Transportation Systems Magazine, 2017, 9 (2): 114- 135
doi: 10.1109/MITS.2017.2666584
|
|
|
[4] |
ZHANG D, ZOU Q, LIN H, et al Automatic pavement defect detection using 3D laser profiling technology[J]. Automation in Construction, 2018, 96: 350- 365
doi: 10.1016/j.autcon.2018.09.019
|
|
|
[5] |
GARCIA-POZUELO D, OLATUNBOSUN O, YUNTA J, et al A novel strain-based method to estimate tire conditions using fuzzy logic for intelligent tires[J]. Sensors, 2017, 17 (2): 350
doi: 10.3390/s17020350
|
|
|
[6] |
REINA G, LEANZA A, MESSINA A Terrain estimation via vehicle vibration measurement and cubature Kalman filtering[J]. Journal of Vibration and Control, 2020, 26 (11/12): 885- 898
|
|
|
[7] |
WANG Y, HU J Y, WANG F A, et al Tire road friction coefficient estimation: review and research perspectives[J]. Chinese Journal of Mechanical Engineering, 2022, 35 (1): 1- 11
doi: 10.1186/s10033-021-00666-0
|
|
|
[8] |
RATH J J, VELUVOLU K C, DEFOORT M Simultaneous estimation of road profile and tire road friction for automotive vehicle[J]. IEEE Transactions on Vehicular Technology, 2014, 64 (10): 4461- 4471
|
|
|
[9] |
李韶华, 王桂洋, 杨泽坤, 等 基于DRBF-EKF算法的车辆质心侧偏角与路面附着系数动态联合估计[J]. 力学学报, 2022, 54 (7): 1853- 1865 LI Shaohua, WANG Guiyang, YANG Zekun, et al Dynamic joint estimation of vehicle sideslip angle and road adhesion coefficient based on DRBF-EKF algorithm[J]. Chinese Journal of Theoretical and Applied Mechanics, 2022, 54 (7): 1853- 1865
|
|
|
[10] |
QI G X, FAN X B, LI H A comparative study of the recursive least squares and fuzzy logic estimation methods for the measurement of road adhesion coefficient[J]. Australian Journal of Mechanical Engineering, 2023, 21 (4): 1230- 1246
doi: 10.1080/14484846.2021.1967839
|
|
|
[11] |
PARK J, MIN K, KIM H, et al Road surface classification using a deep ensemble network with sensor feature selection[J]. Sensors, 2018, 18 (12): 4342
doi: 10.3390/s18124342
|
|
|
[12] |
SUN Z Y, HAO X L, LI W, et al Asphalt pavement friction coefficient prediction method based on genetic-algorithm-improved neural network (GAI-NN) model[J]. Canadian Journal of Civil Engineering, 2022, 49 (1): 109- 120
doi: 10.1139/cjce-2020-0051
|
|
|
[13] |
林棻, 王少博, 赵又群, 等 基于改进 Keras 模型的路面附着系数估计[J]. 机械工程学报, 2021, 57 (12): 74- 86 LIN Fen, WANG Shaobo, ZHAO Youqun, et al Road friction coefficient estimation based on improved Keras model[J]. Journal of Mechanical Engineering, 2021, 57 (12): 74- 86
doi: 10.3901/JME.2021.12.074
|
|
|
[14] |
ŠABANOVIč E, ŽURAULIS V, PRENTKOVSKIS O, et al Identification of road-surface type using deep neural networks for friction coefficient estimation[J]. Sensors, 2020, 20 (3): 612
doi: 10.3390/s20030612
|
|
|
[15] |
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 WU Wenguang, ZHANG Fanhao, XU Menglong Identification of road friction coefficient based on Elman neural network[J]. Journal of Chongqing University, 2023, 46 (3): 118- 128
|
|
|
[16] |
MALHOTRA R, SINGH P. Recent advances in deep learning models: a systematic literature review [J]. Multimedia Tools and Applications , 2023: 1-84.
|
|
|
[17] |
金智林, 严正华 基于二次预测型横向载荷转移率的汽车侧翻预警研究[J]. 中国机械工程, 2019, 30 (15): 1790- 1795 JIN Zhilin, YAN Zhenghua Research on vehicle rollover warning based on secondary predictive lateral load transfer ratio[J]. China Mechanical Engineering, 2019, 30 (15): 1790- 1795
|
|
|
[18] |
PEEIE M H B, OGINO H, OSHINOYA Y Skid control of a small electric vehicle with two in-wheel motors: simulation model of ABS and regenerative brake control[J]. International Journal of Crashworthiness, 2016, 21 (5): 396- 406
doi: 10.1080/13588265.2016.1147731
|
|
|
[19] |
YOU S, GIL J, KIM W Fixed-time slip control with extended-state observer using only wheel speed for anti-lock braking systems of electric vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23 (7): 6368- 6378
|
|
|
[20] |
宋涛. 轮毂驱动电动车的路面附着系数估计方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2017. SONG Tao. Road friction coefficient estimation of in-wheel-motor electric vehicle [D]. Harbin: Harbin Institute of Technology, 2017.
|
|
|
[21] |
AB AZIZ M F, MOSTAFA S A, FOOZY C F M, et al Integrating Elman recurrent neural network with particle swarm optimization algorithms for an improved hybrid training of multidisciplinary datasets[J]. Expert Systems with Applications, 2021, 183: 115441
doi: 10.1016/j.eswa.2021.115441
|
|
|
[22] |
JARI A, AVOKH A PSO-based sink placement and load-balanced anycast routing in multi-sink WSNs considering compressive sensing theory[J]. Engineering Applications of Artificial Intelligence, 2021, 100: 104164
doi: 10.1016/j.engappai.2021.104164
|
|
|
[23] |
彭晓燕, 章兢, 陈昌荣 基于 RBF 神经网络的最佳滑移率在线计算方法[J]. 机械工程学报, 2011, 47 (14): 108- 113 PENG Xiaoyan, ZHANG Jing, CHEN Changrong Calculation of RBF neural network based optimal slip ratio[J]. Journal of Mechanical Engineering, 2011, 47 (14): 108- 113
doi: 10.3901/JME.2011.14.108
|
|
|
[24] |
YANG Y, TANG Q S, BOLIN L, et al Dynamic coordinated control for regenerative braking system and anti-lock braking system for electrified vehicles under emergency braking conditions[J]. IEEE Access, 2020, 8: 172664- 172677
doi: 10.1109/ACCESS.2020.3024918
|
|
|
[25] |
戚尔鹏, 叶鹰 漂移幂函数的数值拟合与理论分析[J]. 情报学报, 2016, 35 (12): 1285- 1295 QI Erpeng, YE Ying Data fitting and theoretical analysis of the shifted power function[J]. Journal of the China Society for Scientific and Technical Information, 2016, 35 (12): 1285- 1295
|
|
|
[26] |
GUO H A simple algorithm for fitting a Gaussian function [DSP tips and tricks][J]. IEEE Signal Processing Magazine, 2011, 28 (5): 134- 137
doi: 10.1109/MSP.2011.941846
|
|
|
[27] |
SUN T J, GAO Z H, GAO F, et al Intelligent vehicle automatic stop-and-go task based on humanized learning control model[J]. Advances in Civil Engineering, 2021, 2021: 1- 11
|
|
|
[28] |
PANCHAL G, GANATRA A, KOSTA Y P, et al Behaviour analysis of multilayer perceptrons with multiple hidden neurons and hidden layers[J]. International Journal of Computer Theory and Engineering, 2011, 3 (2): 332- 337
|
|
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|