Mass estimation method for intelligent vehicles based on fusion of machine learning and vehicle dynamic model
Tóm tắt
Vehicle mass is an important parameter for motion control of intelligent vehicles, but is hard to directly measure using normal sensors. Therefore, accurate estimation of vehicle mass becomes crucial. In this paper, a vehicle mass estimation method based on fusion of machine learning and vehicle dynamic model is introduced. In machine learning method, a feedforward neural network (FFNN) is used to learn the relationship between vehicle mass and other state parameters, namely longitudinal speed and acceleration, driving or braking torque, and wheel angular speed. In dynamics-based method, recursive least square (RLS) with forgetting factor based on vehicle dynamic model is used to estimate the vehicle mass. According to the reliability of each method under different conditions, these two methods are fused using fuzzy logic. Simulation tests under New European Driving Cycle (NEDC) condition are carried out. The simulation results show that the estimation accuracy of the fusion method is around 97%, and that the fusion method performs better stability and robustness compared with each single method.
Tài liệu tham khảo
A. Ahmed, J. Santhosh, F. Aldbea, Vehicle dynamics modeling and simulation with control using single track model, in 2020 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE) (IEEE, Bhubaneswar, 2020)
J. Ma, J. Hu, E. Leslie, F. Zhou, P. Huang, J. Bared, An eco-drive experiment on rolling terrains for fuel consumption optimization with connected automated vehicles. Transp. Res., Part C, Emerg. Technol. 100, 125–141 (2019)
Y. Liu, W. Wang, A safety reinforced cooperative adaptive cruise control strategy accounting for dynamic vehicle-to-vehicle communication failure. Sensors 21(18), 1–16 (2021)
Y. Zhang, J. Yin, Research on ABS logic sliding mode control method based on road surface recognition, in 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) (IEEE, Chengdu, 2019), pp. 2185–2189
Y. Zhang, Y. Zhang, Z. Ai, Y. Feng, J. Zhang, Y. Murphey, Estimation of electric mining haul trucks’ mass and road slope using dual level reinforcement estimator. IEEE Trans. Veh. Technol. 68(11), 10627–10638 (2019)
K. Seungki, S. Kyungsik, Y. Changhee, K. Huh, Development of algorithms for commercial vehicle mass and road grade estimation. Int. J. Automot. Technol. 18(6), 1077–1083 (2017)
L. Cai, H. Wang, T. Jia, P. Peng, D. Pi, E. Wang, Two-layer structure algorithm for estimation of commercial vehicle mass. Proc. Inst. Mech. Eng., Part D, J. Automob. Eng. 234(2–3), 378–389 (2020)
J. Zhao, Z. Li, B. Zhu, Y. Li, Y. Sun, Vehicle mass and road slope estimation based on interactive multi-model. Zhongguo Gonglu Xuebao 32(12), 58–65 (2019)
Y. Sun, L. Li, B. Yan, C. Yang, G. Tang, A hybrid algorithm combining EKF and RLS in synchronous estimation of road grade and vehicle mass for a hybrid electric bus. Mech. Syst. Signal Process. 68–69, 416–430 (2016)
M. Hu, Y. Luo, L. Chen, K. Li, Vehicle mass estimation based on longitudinal frequency response characteristics. Jilin Daxue Xuebao (Gongxueban) 48(4), 977–983 (2018)
W. Chu, K. Cao, S. Li, Y. Luo, K. Li, Vehicle mass estimation based on high-frequency-information extraction, in 7th International Federation of Automatic Control (IFAC) Symposium on Advances in Automotive Control (IFAC, Tokyo, 2013), pp. 72–76
C. Shih, P. Huang, E. Yen, P. Tsung, Vehicle speed prediction with RNN and attention model under multiple scenarios, in 2019 IEEE Intelligent Transportation Systems Conference (ITSC) (IEEE, New Zealand, 2019), pp. 369–375
S. Torabi, M. Wahde, P. Hartono, Road grade and vehicle mass estimation for heavy-duty vehicles using feedforward neural networks, in 4th International Conference on Intelligent Transportation Engineering (ICITE) (IEEE, Singapore, 2019), pp. 316–321
A. Korayem, A. Khajepour, B. Fidan, Trailer mass estimation using system model-based and machine learning approaches. IEEE Trans. Veh. Technol. 69(11), 12536–12546 (2020)
Z. Wang, K. Han, P. Tiwari, Motion estimation of connected and automated vehicles under communication delay and packet loss of V2X communications, in SAE 2021 WCX Digital Summit (SAE International, 2021)
N. Lin, S. Shi, L. Ma, H. Kui, Road grade estimation with grade change rate information. Jilin Daxue Xuebao (Gongxueban) 46(6), 1845–1850 (2016)
P. Sahlholm, K. Johansson, Road grade estimation for look-ahead vehicle control using multiple measurement runs. Control Eng. Pract. 18(11), 1328–1341 (2010)
C. Boucher, J. Noyer, A general framework for 3-D parameters estimation of roads using GPS, OSM and DEM data. Sensors 18(1), 25–29 (2018)
A. Ribeiro, A. Moutinho, A. Fioravanti, E. Paiva, Estimation of tire-road friction for road vehicles: a time delay neural network approach. J. Braz. Soc. Mech. Sci. Eng. 42(4), 1–12 (2020)
Ministry of Transport of the People’s Republic of China, Technical Standard of Highway Engineering (China Communications Press, Beijing, 2014), pp. 15–16
D. Zhang, L. Chen, Y. Wang, H. Wang, The research on improving the precision of the polymer IFHI by BP neural network of the method data normalization. IOP Conf. Ser. Earth Environ. Sci. 692(3), 1–7 (2021)
K. He, X. Zhang, S. Ren, J. Sun, Delving deep into rectifiers: surpassing human-level performance on ImageNet classification, in Proceedings of the IEEE International Conference on Computer Vision (arXiv, New York City, 2015), pp. 1026–1034
C. Pan, G. Xie, Convergence of online gradient method with momentum for BP neural network. IOP Conf. Ser. Earth Environ. Sci. 1802(4), 1–4 (2020)
Y. Fang, Z. Yang, X. Zhou, Impact of curve radius and spiral length on steering behavior on two-lane highway. J. Transp. Syst. Eng. Inf. Technol. 21(1), 116–123
J. Slotine, W. Li, Applied Nonlinear Control (Prentice Hall, New Jersey, 1991), pp. 187–190