Abstract
Modern control synthesis assumes that observability of a dynamic system is satisfied. However, in particular, observability may not be met due to manufacturing cost. To cope with this challenging dilemma, we consider training a neural network with a large dataset that contains prior information of a given nonlinear vehicle dynamics system. In this paper, we proposed and designed a long short-term memory (LSTM)-based neural network to estimate the velocity and position states of a full car’s suspension system using only online data streams from cheap inertial sensory measurements. In the training stage, we collect the input and output data that we want to reconstruct using a nonlinear full car model simulation. An LSTM-based neural network is subsequently trained with the collected data, and it reconstructs the velocity and position states only from the acceleration information inputs in the production stage. Finally, to further enhance the performance via Bayesian filtering, the neural network’s outputs are projected into the vehicle dynamics using the extended Kalman filter. To demonstrate the effectiveness of our approach, we compare the performance of the proposed method against a conventional kinematic Kalman filter. The results show that the proposed method recorded 148.8 times smaller value in terms of the mean squared error (MSE) than that of the benchmark. Furthermore, we analyzed the sensitivity of the proposed neural network with or without gyroscope sensors in the full car model. Then, an illustrative control example for implementing the proposed method is presented. Our approach shows that with only noisy accelerometer and gyroscope sensors, we can successfully reconstruct nearly perfect states in a full car’s nonlinear dynamic system using a well-trained LSTM-based neural network combined with the extended Kalman filter.
Similar content being viewed by others
References
Alamdari, A., Sovizi, J., Krovi, V.N.: Enhanced full-state estimation and dynamic-model-based prediction for road-vehicles. In: ASME 2014 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. American Society of Mechanical Engineers Digital Collection (2014)
Bar-Shalom, Y., Li, X.R., Kirubarajan, T.: Estimation with Applications to Tracking and Navigation: Theory Algorithms and Software. Wiley (2004)
Carratù, M., Pietrosanto, A., Sommella, P., Paciello, V.: Velocity prediction from acceleration measurements in motorcycle suspensions. In: 2017 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), pp. 1–6. IEEE (2017)
Challa, S., Bar-Shalom, Y.: Nonlinear filter design using Fokker–Planck–Kolmogorov probability density evolutions. IEEE Trans. Aerosp. Electron. Syst. 36(1), 309–315 (2000)
Chen, S., Billings, S., Grant, P.: Non-linear system identification using neural networks. Int. J. Control 51(6), 1191–1214 (1990)
Chen, Z., et al.: Bayesian filtering: from Kalman filters to particle filters, and beyond. Statistics 182(1), 1–69 (2003)
Cheng, Y., Karjala, T.W., Himmelblau, D.M.: Identification of nonlinear dynamic processes with unknown and variable dead time using an internal recurrent neural network. Ind. Eng. Chem. Res. 34(5), 1735–1742 (1995)
Codevilla, F., Miiller, M., López, A., Koltun, V., Dosovitskiy, A.: End-to-end driving via conditional imitation learning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 1–9. IEEE (2018)
Davoodabadi, I., Ramezani, A.A., Mahmoodi-k, M., Ahmadizadeh, P.: Identification of tire forces using dual unscented Kalman filter algorithm. Nonlinear Dyn. 78(3), 1907–1919 (2014)
Dugard, L., Sename, O., Aubouet, S., Talon, B.: Full vertical car observer design methodology for suspension control applications. Control Eng. Practice 20(9), 832–845 (2012)
Gamse, S.: Dynamic modelling of displacements on an embankment dam using the Kalman filter. J. Spat. Sci. 63(1), 3–21 (2018)
Gamse, S., Nobakht-Ersi, F., Sharifi, M.A.: Statistical process control of a Kalman filter model. Sensors 14(10), 18053–18074 (2014)
García, S.D., Patino, D.: Estimation based on acceleration measures of an active suspension plant. In: 2015 IEEE 2nd Colombian Conference on Automatic Control (CCAC), pp. 1–6. IEEE (2015)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Hu, G., Gao, B., Zhong, Y., Gu, C.: Unscented Kalman filter with process noise covariance estimation for vehicular INS/GPS integration system. Inf. Fusion 64, 194–204 (2020)
Jeon, S.: State estimation based on kinematic models considering characteristics of sensors. In: Proceedings of the 2010 American Control Conference, pp. 640–645. IEEE (2010)
Karim, F., Majumdar, S., Darabi, H., Chen, S.: LSTM fully convolutional networks for time series classification. IEEE Access 6, 1662–1669 (2017)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Martens, W., von Wagner, U., Mehrmann, V.: Calculation of high-dimensional probability density functions of stochastically excited nonlinear mechanical systems. Nonlinear Dyn. 67(3), 2089–2099 (2012)
Múčka, P.: Simulated road profiles according to iso 8608 in vibration analysis. J. Test. Eval. 46(1), 405–418 (2017)
Muratore, F., Gienger, M., Peters, J.: Assessing transferability from simulation to reality for reinforcement learning. IEEE Trans. Pattern Anal. Mach. Intell. (2019)
Nagamune, R., Choi, J.: Parameter reduction in estimated model sets for robust control. J. Dyn. Syst. Meas. Control 132(2) (2010)
Neal, R.M.: Priors for infinite networks. In: Bayesian Learning for Neural Networks, pp. 29–53. Springer (1996)
Nirmal, K., Sreejith, A., Mathew, J., Sarpotdar, M., Suresh, A., Prakash, A., Safonova, M., Murthy, J.: Noise modeling and analysis of an imu-based attitude sensor: improvement of performance by filtering and sensor fusion. In: Advances in Optical and Mechanical Technologies for Telescopes and Instrumentation II, vol. 9912, p. 99126W. International Society for Optics and Photonics (2016)
Park, J., Son, H., Lee, J., Choi, J.: Driving assistant companion with voice interface using long short-term memory networks. IEEE Trans. Ind. Inf. 15(1), 582–590 (2018)
Peng, X.B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Sim-to-real transfer of robotic control with dynamics randomization. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 1–8. IEEE (2018)
Pesce, V., Silvestrini, S., Lavagna, M.: Radial basis function neural network aided adaptive extended Kalman filter for spacecraft relative navigation. Aerosp. Sci. Technol. 96, 105527 (2020)
Poussot-Vassal, C., Sename, O., Dugard, L., Gaspar, P., Szabo, Z., Bokor, J.: A new semi-active suspension control strategy through LPV technique. Control Eng. Practice 16(12), 1519–1534 (2008)
Savaresi, S.M., Poussot-Vassal, C., Spelta, C., Sename, O., Dugard, L.: Semi-active Suspension Control Design for Vehicles. Elsevier (2010)
Smyth, A., Wu, M.: Multi-rate Kalman filtering for the data fusion of displacement and acceleration response measurements in dynamic system monitoring. Mech. Syst. Signal Process. 21(2), 706–723 (2007)
Sobczyk, K.: Stochastic nonlinear systems. Existing methods and new results. ZAMM 78(10), 651–661 (1998)
Srinivasan, B., Prasad, U.R., Rao, N.J.: Back propagation through adjoints for the identification of nonlinear dynamic systems using recurrent neural models. IEEE Trans. Neural Netw. 5(2), 213–228 (1994)
Von Wagner, U.: On non-linear stochastic dynamics of quarter car models. Int. J. Non-Linear Mech. 39(5), 753–765 (2004)
von Wagner, U., Wedig, W.V.: On the calculation of stationary solutions of multi-dimensional Fokker–Planck equations by orthogonal functions. Nonlinear Dyn. 21(3), 289–306 (2000)
Wang, X., Qin, W., Wang, Y., Cui, N.: Bayesian filtering based on solving the Fokker–Planck equation. Aircr. Eng. Aerosp. Technolo. 90(2), 312–319 (2018)
Wang, Z., Dong, M., Qin, Y., Du, Y., Zhao, F., Gu, L.: Suspension system state estimation using adaptive Kalman filtering based on road classification. Veh. Syst. Dyn. 55(3), 371–398 (2017)
Williams, C.K.: Computing with infinite networks. In: Advances in Neural Information Processing Systems, pp. 295–301 (1997)
Yi, K., Suk Song, B.: Observer design for semi-active suspension control. Veh. Syst. Dyn. 32(2–3), 129–148 (1999)
Zaheer, M., Ahmed, A., Smola, A.J.: Latent lstm allocation joint clustering and non-linear dynamic modeling of sequential data. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 3967–3976. JMLR.org (2017)
Zhang, G., Yu, Z., Wang, J.: Correction of contaminated yaw rate signal and estimation of sensor bias for an electric vehicle under normal driving conditions. Mech. Syst. Signal Process. 87, 64–80 (2017)
Zhang, L., Jiang, Z., Choi, J., Lim, C.Y., Maiti, T., Baek, S.: Patient-specific prediction of abdominal aortic aneurysm expansion using Bayesian calibration. IEEE J. Biomed. Health Inf. 23(6), 2537–2550 (2019)
Zheng, X., Zaheer, M., Ahmed, A., Wang, Y., Xing, E.P., Smola, A.J.: State space LSTM models with particle mcmc inference. arXiv preprint arXiv:1711.11179 (2017)
Zhu, Q., Ishitobi, M.: Chaotic vibration of a nonlinear full-vehicle model. Int. J. Solids Struct. 43(3–4), 747–759 (2006)
Acknowledgements
This work was supported in part by the National Research Foundation of Korea grant funded by the Korea government (Ministry of Science and Information Technology, 2021R1A2B5B01002620) and in part by the Ministry of Culture, Sports and Tourism (MCST) and the Korea Creative Content Agency (KOCCA) thorugh the Culture Technology (CT) Research & Development Program 2019 (R2019020038).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yong, H., Seo, J., Kim, J. et al. State reconstruction in a nonlinear vehicle suspension system using deep neural networks. Nonlinear Dyn 105, 439–455 (2021). https://doi.org/10.1007/s11071-021-06598-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11071-021-06598-7