Deep neural network based data-driven virtual sensor in vehicle semi-active suspension real-time control
Abstract
This research presents a data-driven Neural Network (NN)-based Virtual Sensor (VS) that estimates vehicles’ Unsprung Mass (UM) vertical velocity in real-time. UM vertical velocity is an input parameter used to control a vehicle’s semi-active suspension. The extensive simulation-based dataset covering 95 scenarios was created and used to obtain training, validation and testing data for Deep Neural Network (DNN). The simulations have been performed with an experimentally validated full vehicle model using software for advanced vehicle dynamics simulation. VS was developed and tested, taking into account the Root Mean Square (RMS) of Sprung Mass (SM) acceleration as a comfort metric. The RMS was calculated for two cases: using actual UM velocity and estimations from the VS as input to the suspension controller. The comparison shows that RMS change is less than the difference threshold that vehicle occupants could perceive. The achieved result indicates the great potential of using the proposed VS in place of the physical sensor in vehicles.
Keyword : virtual sensor, real-time, semi-active suspension, vehicle dynamics, deep neural network, deep learning
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Ahamed, P. S. S.; Duraiswamy, P. 2019. Virtual sensing active noise control system with 2d microphone array for automotive applications, in 2019 6th International Conference on Signal Processing and Integrated Networks (SPIN), 7–8 March 2019, Noida, India, 151–155. https://doi.org/10.1109/spin.2019.8711608
Al-Ashmori, M.; Wang, X. 2020. A systematic literature review of various control techniques for active seat suspension systems, Applied Sciences 10(3): 1148. https://doi.org/10.3390/app10031148
Cao, D.; Song, X.; Ahmadian, M. 2011. Editors’ perspectives: road vehicle suspension design, dynamics, and control, Vehicle System Dynamics: International Journal of Vehicle Mechanics and Mobility 49(1–2): 3–28. https://doi.org/10.1080/00423114.2010.532223
Choi, Y.; Yoon, S. 2020. Virtual sensor-assisted in situ sensor calibration in operational HVAC systems, Building and Environment 181: 107079. https://doi.org/10.1016/j.buildenv.2020.107079
Fares, A.; Bani Younes, A. 2020. Online reinforcement learning-based control of an active suspension system using the actor critic approach, Applied Sciences 10(22): 8060. https://doi.org/10.3390/app10228060
Floreán-Aquino, K. H.; Arias-Montiel, M.; Linares-Flores, J.; Mendoza-Larios, J. G.; Cabrera-Amado, Á. 2021. Modern semi-active control schemes for a suspension with MR actuator for vibration attenuation, Actuators 10(2): 22. https://doi.org/10.3390/act10020022
Ghoniem, M.; Awad, T.; Mokhiamar, O. 2020. Control of a new low-cost semi-active vehicle suspension system using artificial neural networks, Alexandria Engineering Journal 59(5): 4013–4025. https://doi.org/10.1016/j.aej.2020.07.007
Gräbe, R. P.; Kat, C.-J.; Van Staden, P. J.; Els, P. S. 2020. Difference thresholds for a vehicle on a 4-poster test rig, Applied Ergonomics 87: 103115. https://doi.org/10.1016/j.apergo.2020.103115
Jain, S.; Saboo, S.; Pruncu, C. I.; Unune, D. R. 2020. Performance investigation of integrated model of quarter car semi-active seat suspension with human model, Applied Sciences 10(9): 3185. https://doi.org/10.3390/app10093185
Jeong, K.; Choi, S. B. 2019. Vehicle suspension relative velocity estimation using a single 6-D IMU sensor, IEEE Transactions on Vehicular Technology 68(8): 7309–7318. https://doi.org/10.1109/tvt.2019.2920876
Jiang, H.; Wang, C.; Li, Z.; Liu, C. 2021. Hybrid model predictive control of semiactive suspension in electric vehicle with hub-motor, Applied Sciences 11(1): 382. https://doi.org/10.3390/app11010382
Jierula, A.; Wang, S.; Oh, T.-M.; Wang, P. 2021. Study on accuracy metrics for evaluating the predictions of damage locations in deep piles using artificial neural networks with acoustic emission data, Applied Sciences 11(5): 2314. https://doi.org/10.3390/app11052314
Kahraman, K.; Emirler, M. T.; Centürk, M.; Güvenç, B. A.; Güvenç, L.; Efendioǧlu, B. 2010. Estimation of vehicle yaw rate using a virtual sensor with a speed scheduled observer, IFAC Proceedings Volumes 43(7): 632–637. https://doi.org/10.3182/20100712-3-de-2013.00043
Khatibisepehr, S.; Huang, B.; Khare, S. 2013. Design of inferential sensors in the process industry: a review of Bayesian methods, Journal of Process Control 23(10): 1575–1596. https://doi.org/10.1016/j.jprocont.2013.05.007
Kim, G.; Lee, S. Y.; Oh, J.-S.; Lee, S. 2021. Deep learning-based estimation of the unknown road profile and state variables for the vehicle suspension system, IEEE Access 9: 13878–13890. https://doi.org/10.1109/access.2021.3051619
Koch, G. P. A. 2011. Adaptive Control of Mechatronic Vehicle Suspension Systems. PhD Dissertation. Technical University of Munich, Germany. 250 p. Available from Internet: http://mediatum.ub.tum.de/doc/1002476/document.pdf
Konoiko, A.; Kadhem, A.; Saiful, I.; Ghorbanian, N.; Zweiri, Y.; Sahinkaya, M. N. 2019. Deep learning framework for controlling an active suspension system, Journal of Vibration and Control 25(17): 2316–2329. https://doi.org/10.1177/1077546319853070
LAKD. 2010. Inžinerinių saugaus eismo priemonių projektavimo ir naudojimo rekomendacijos R ISEP 10. Lietuvos automobilių kelių direkcija (LAKD) prie Susisiekimo ministerijos, Vilnius, 127 p. Available from Internet: https://e-seimas.lrs.lt/portal/legalAct/lt/TAD/TAIS.375622
Li, H.; Yu, D.; Braun, J. E. 2011. A review of virtual sensing technology and application in building systems, HVAC&R Research 17(5): 619–645.
Liu, C.; Chen, L.; Yang, X.; Zhang, X.; Yang, Y. 2019. General theory of skyhook control and its application to semi-active suspension control strategy design, IEEE Access 7: 101552–101560. https://doi.org/10.1109/access.2019.2930567
Marques, T.; Reynoso-Meza, G. 2020. Applications of multi-objective optimisation for PID-like controller tuning: a 2015–2019 review and analysis, IFAC-PapersOnLine 53(2): 7933–7940. https://doi.org/10.1016/j.ifacol.2020.12.2140
Martin, D.; Kühl, N.; Satzger, G. 2021. Virtual sensors, Business & Information Systems Engineering 63(3): 315–323. https://doi.org/10.1007/s12599-021-00689-w
Mattera, C. G.; Quevedo, J.; Escobet, T.; Shaker, H. R.; Jradi, M. 2018. A method for fault detection and diagnostics in ventilation units using virtual sensors, Sensors 18(11): 3931. https://doi.org/10.3390/s18113931
Milanese, M.; Ruiz, F.; Taragna, M. 2007. Linear virtual sensors for vertical dynamics of vehicles with controlled suspensions, in 2007 European Control Conference (ECC), 2–5 July 2007, Kos, Greece, 1257–1263. https://doi.org/10.23919/ecc.2007.7068662
Mozaffari, A.; Chenouri, S.; Qin, Y.; Khajepour, A. 2019. Learning-based vehicle suspension controller design: a review of the state-of-the-art and future research potentials, eTransportation 2: 100024. https://doi.org/10.1016/j.etran.2019.100024
Omrane, I.; Etien, E.; Dib, W.; Bachelier, O. 2015. Modeling and simulation of soft sensor design for real-time speed and position estimation of PMSM, ISA Transactions 57: 329–339. https://doi.org/10.1016/j.isatra.2014.06.004
Pellegrini, E. 2012. Model-Based Damper Control for Semi-Active Suspension Systems. PhD Dissertation. Technical University of Munich, Germany. 196 p. Available from Internet: https://mediatum.ub.tum.de/doc/1113007/document.pdf
Pletschen, N.; Badur, P. 2014. Nonlinear state estimation in suspension control based on Takagi–Sugeno model, IFAC Proceedings Volumes 47(3): 11231–11237. https://doi.org/10.3182/20140824-6-za-1003.02500
Qin, Y.; He, C.; Ding, P.; Dong, M.; Huang, Y. 2018. Suspension hybrid control for in-wheel motor driven electric vehicle with dynamic vibration absorbing structures, IFAC-PapersOnLine 51(31): 973–978. https://doi.org/10.1016/j.ifacol.2018.10.054
Sathishkumar, P.; Wang, R.; Yang, L.; Thiyagarajan, J. 2021. Energy harvesting approach to utilize the dissipated energy during hydraulic active suspension operation with comfort oriented control scheme, Energy 224: 120124. https://doi.org/10.1016/j.energy.2021.120124
Savaresi, D.; Favalli, F.; Formentin, S.; Savaresi, S. M. 2019. On-line damping estimation in road vehicle semi-active suspension systems, IFAC-PapersOnLine 52(5): 679–684. https://doi.org/10.1016/j.ifacol.2019.09.108
Savaresi, S. M.; Poussot-Vassal, C.; Spelta, C.; Sename, O.; Dugard, L. 2010. Classical control for semi-active suspension system, in Semi-Active Suspension Control Design for Vehicles, Chapter 6, 107–120. https://doi.org/10.1016/b978-0-08-096678-6.00006-7
Savitski, D.; Schleinin, D.; Ivanov, V.; Augsburg, K. 2017. Sliding mode approach in semi-active suspension control, in A. Ferrara (Ed.). Sliding Mode Control of Vehicle Dynamics, 191–228. https://doi.org/10.1049/PBTR005E_ch6
Skrickij, V.; Savitski, D.; Ivanov, V.; Skačkauskas, P. 2018. Investigation of cavitation process in monotube shock absorber, International Journal of Automotive Technology 19(5): 801–810. https://doi.org/10.1007/s12239-018-0077-1
Soliman, A. M. A.; Kaldas, M. M. S. 2021. Semi-active suspension systems from research to mass-market – a review, Journal of Low Frequency Noise, Vibration and Active Control 40(2): 1005–1023. https://doi.org/10.1177/1461348419876392
Son, T. D.; Bhave, A.; Vandermeulen, W.; Geluk, T.; Worm, M.; Van der Auweraer, H. 2020. Model-Based and Data-Driven Learning Control for Safety and Comfort for Autonomous Driving. White Paper. Siemens, Plano, TX, US. 16 p. https://doi.org/10.13140/RG.2.2.13850.88003
Sun, S.-B.; He, Y.-Y.; Zhou, S.-D.; Yue, Z.-J. 2017. A data-driven response virtual sensor technique with partial vibration measurements using convolutional neural network, Sensors 17(12): 2888. https://doi.org/10.3390/s17122888
Šabanovič, E.; Kojis, P.; Šukevičius, Š.; Shyrokau, B.; Ivanov, V.; Dhaens, M.; Skrickij, V. 2021. Feasibility of a neural network-based virtual sensor for vehicle unsprung mass relative velocity estimation, Sensors 21(21): 7139. https://doi.org/10.3390/s21217139
Theunissen, J.; Tota, A.; Gruber, P.; Dhaens, M.; Sorniotti, A. 2021. Preview-based techniques for vehicle suspension control: a state-of-the-art review, Annual Reviews in Control 51: 206–235. https://doi.org/10.1016/j.arcontrol.2021.03.010
Vandersmissen, B.; Six, K.; Reybrouck, K. 2012. ACOCAR: ultimate comfort and safety through the energy-efficient active damping system of Tenneco, in 21st Aachen Colloquium Automobile and Engine Technology 2012, 8–10 October 2012, Aachen, Germany. 15 p. Available from Internet: https://www.aachener-kolloquium.de/images/tagungsunterlagen/2012_21._ACK/C3.3_Reybrouck_Tenneco.pdf
Viehweger, M.; Vaseur, C.; Van Aalst, S.; Acosta, M.; Regolin, E.; Alatorre, A.; Desmet, W.; Naets, F.; Ivanov, V.; Ferrara, A.; Victorino, A. 2021. Vehicle state and tyre force estimation: demonstrations and guidelines, Vehicle System Dynamics: International Journal of Vehicle Mechanics and Mobility 59(5): 675–702. https://doi.org/10.1080/00423114.2020.1714672
Yatak, M. Ö., Şahin, F. 2021. Ride comfort-road holding trade-off improvement of full vehicle active suspension system by interval type-2 fuzzy control, Engineering Science and Technology, an International Journal 24(1): 259–270. https://doi.org/10.1016/j.jestch.2020.10.006
Zaharia, C.; Clenci, A. 2013. Study on virtual sensors and their automotive applications, Scientific Bulletin – Automotive Series (23): 68–74. Available from Internet: https://automotive.upit.ro/index_files/2013/2013_A_8_.pdf
Zheng, Y.; Shyrokau, B.; Keviczky, T.; Al Sakka M.; Dhaens, M. 2021. Curve tilting with nonlinear model predictive control for enhancing motion comfort, IEEE Transactions on Control Systems Technology (Early Access): 1–12. https://doi.org/10.1109/TCST.2021.3113037
Zhou, C.; Liu, X.; Chen, W.; Xu, F.; Cao, B. 2018. Optimal sliding mode control for an active suspension system based on a genetic algorithm, Algorithms 11(12): 205. https://doi.org/10.3390/a11120205