Road Friction Coefficient Estimation Based on Improved Keras Model

doi:10.3901/JME.2021.12.074

Abstract

Abstract: Road friction coefficient is one of the most important parameters in vehicle-road interaction, the accurate acquisition of road friction coefficient is the basis for proper functioning of the vehicle's active safety control system. A method for estimating road friction coefficient based on an improved Keras model is proposed. Conduct a vehicle dynamic analysis to find out the dynamic parameters related to road friction coefficient which as the input of the neural network model. A data set is established through simulation experiments by various driving conditions. Based on the Keras model, combined with a limiting recursive average filtering algorithm, K-fold verification, Dropout regularization, and Sarsa reinforcement learning, an improved Keras model for road friction coefficient estimator is proposed. The filtering algorithm is used to remove the noise of the neural network model's input. K-fold verification is used to expand the sample space. Dropout regularization can reduce the model's overfitting phenomenon and improve the generalization ability of the model. Sarsa reinforcement learning can deal with the problem that road friction coefficient beyond borders. The simulation verification shows the effectiveness and reliability of the designed estimator for road friction coefficient. Compared with the original keras model, the average absolute error and root mean square error of the proposed method are reduced by 73% and 58% respectively.

Key words: road friction coefficient, neural network, Keras model, reinforcement learning, estimation

CLC Number:

U461

LIN Fen, WANG Shaobo, ZHAO Youqun, CAI Yizhang. Road Friction Coefficient Estimation Based on Improved Keras Model[J]. Journal of Mechanical Engineering, 2021, 57(12): 74-86.

References

[1] 余卓平, 左建令, 张立军. 路面附着系数估算技术发展现状综述[J]. 汽车工程, 2006(6):546-549. YU Zhuoping, ZUO Jianling, ZHANG Lijun. A summary on the development status quo of tire-road friction coefficient estimation techniques[J]. Automotive Engineering, 2006(6):546-549.
[2] 袁朝春, 张龙飞, 陈龙. 路面附着系数识别方法发展现状综述及展望[J]. 机械制造与自动化, 2018, 47(2):4-7. YUAN Chaochun, ZHANG Longfei, CHEN Long. Summary and prospect of development of road coefficient identification methods[J]. Mechanical Manufacture and Automation, 2018, 47(2):4-7.
[3] JIN X J, YIN G D, CHEN N. Advanced estimation techniques for vehicle system dynamic state:a survey[J]. Sensors, 2019, 19(19):4289-4315.
[4] HUANG B, FU X, HUANG S. Calculation algorithm of tire-road friction coefficient based on limited-memory adaptive extended kalman filter[J]. Mathematical Problems in Engineering, 2019, 10(5):1155-1169.
[5] RAJENDRAN S, SPURGEON SK, TSAMPA-RDOUKAS G. Estimation of road frictional force and wheel slip for effective antilock braking system (ABS) control[J]. International Journal of Robust and Nonlinear Control, 2019, 29(3):736-765.
[6] GUO H Y, YIN Z Y, CAO D P. A review of estimation for vehicle tire-road interactions toward automated driving[J]. IEEE Transactions on Systems Man Cybernetics-Systems, 2019, 49(1):14-30.
[7] XIONG Y, YANG X G. A review on in-tire sensor systems for tire-road interaction studies[J]. Sensor Review, 2018, 38(2):231-238.
[8] GAO L T, XIONG L, LIN X F, et al. Multi-sensor fusion road friction coefficient estimation during steering with lyapunov method[J]. Sensors, 2019, 19(18):3816-3833.
[9] ACOSTA M, KANARACHOS S, BLUNDELL M. Virtual tyre force sensors:an overview of tyre model-based and tyre model-less state estimation techniques[J]. Proceedings of The Institution of Mechanical Engineers Part D-Journal of Automobile Engineering, 2018, 232(14):1883-1930.
[10] LI X Y, XU N, LI Q, et al. A fusion methodology for sideslip angle estimation on the basis of kinematics-based and model-based approaches[J]. Proceedings of The Institution of Mechanical Engineers Part D-Journal of Automobile Engineering, 2019, 10(14):1177-1191.
[11] PAUL D, VELENIS E, HUMBERT F, et al. Tyre-road friction μ-estimation based on braking force distribution[J]. Proceedings of The Institution of Mechanical Engineers Part D-Journal of Automobile Engineering, 2019, 233(8):2030-2047.
[12] PARK G, HWANG Y, CHOI S B. Vehicle positioning based on velocity and heading angle observer using low-cost sensor fusion[J]. Journal of Dynamic Systems Measurement and Control-Transactions of the ASME, 2017, 139(12):1115-1128.
[13] RIBEIRO A M, MOUTINHO A, FIORAVANTI A R, et al. Estimation of tire-road friction for road vehicles a time delay neural network approach[J]. Journal of The Brazilian Society of Mechanical Sciences and Engineering, 2020, 42(1):1007-1025.
[14] DAE J K, JIN S K, SEUNG H L, et al. A comparative study of estimating road surface condition using support vector machine and deep neural network[C]//IEEE Intelligent Transportation Systems Conference (ITSC), Auckland, NZ, October 27-30, 2019, 1066-1071.
[15] SABANOVIC E, ZURAULIS V, PRENTKOVSKIS O, et al. Identification of road-surface type using deep neural networks for friction coefficient estimation[J]. Sensors, 2020, 20(3):3390-3407.
[16] 汪涛. 面向商用车的路面附着系数估计研究[D]. 重庆:重庆邮电大学, 2019. WANG Tao. Estimation of road adhesion coefficient for commercial vehicles[D]. Chongqing:Chongqing University of Posts and Telecommunications, 2019.
[17] 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.
[18] WU B F, CHANG P J, CHEN Y S, et al. An intelligent wheelchair anti-lock braking system design with friction coefficient estimation[J]. IEEE Access, 2018(6):73686-73701.
[19] ZAREIAN A, AZADI S, KAZEMI R. Estimation of road friction coefficient using extended kalman filter, recursive least square, and neural network[J]. Proceedings of The Institution of Mechanical Engineers Part K-Journal of Multi-Body Dynamics, 2016, 230(1):52-68.
[20] LU Y Z, YAN D P, LEVY D. Friction coefficient estimation in servo systems using neural dynamic programming inspired particle swarm search[J]. Applied Intelligence, 2015, 43(1):1-14.
[21] LUQUE P, MANTARAS D A, FIDALGO E, et al. Tyre-road grip coefficient assessment-part Ⅱ:online estimation using instrumented vehicle, extended kalman filter, and neural network[J]. Vehicle System Dynamics, 2013, 51(12):1872-1893.
[22] HE R, JIMENEZ E, SAVITSKI D, et al. Investigating the parameterization of dugoff tire model using experimental tire-ice data[J]. SAE International Journal of Passenger Cars-Mechanical Systems, 2017, 10(1):83-92.
[23] 郭健忠, 程峰, 谢斌, 等. 改进型限幅递推平均滤波法在燃油表中的应用[J]. 科学技术与工程, 2018, 18(16):62-67. GUO Jianzhong, CHENG Feng, XIE Bin, et al. Application of improved amplitude limiting recursive average filtering algorithm in fuel gauge[J]. Science Technology and Engineering, 2018, 18(16):62-67.
[24] LEE H, SONG J. Introduction to convolutional neural network using keras; an understanding from a statistician[J]. Communications for Statistical Applications and Methods, 2019, 26(6):591-610.
[25] BARROW D K, CRONE S F. Cross-validation aggregation for combining autoregressive neural network forecasts[J]. International Journal of Forecasting, 2016, 32(4):1120-1137.
[26] ANDRECUT M, ALI M K. Deep-sarsa:a reinforcement learning algorithm for autonomous navigation[J]. International Journal of Modern Physics C, 2001, 12(10):1513-1523.
[27] GAO W, ZHOU Z H. Dropout rademacher complexity of deep neural networks[J]. Science China-Information Sciences, 2016, 59(7):1007-1019.