Design of a distributed hybrid model predictive controller based on long short-term memory networks model for hub-motor electric vehicle with air suspension
Restricted accessResearch articleFirst published online April, 2026
Design of a distributed hybrid model predictive controller based on long short-term memory networks model for hub-motor electric vehicle with air suspension
The vigorous development of hub-motor electric vehicles (HMEVs) is driven by their potential to significantly enhance energy efficiency, handling performance and space utilization, as well as reduce mechanical losses and maintenance costs. The unbalanced electromagnetic force (UEMF) is generated by the combined effect of the hub-motor and the road coupling excitation, which is a major challenge to reduce performance deterioration in HMEVs. A Distributed Hybrid Model Predictive Control (DHMPC) strategy is introduced in this paper for HMEVs equipped with air suspension (AS) to improve vehicle ride comfort and handling stability. UEMF is calculated based on analytic method and optimized by LSTM. An 11-DOF full-vehicle is established by distributive method and verified by vehicle test. Based on LSTM online training and dynamic modelling, a DHMPC controller integrates nonlinear damping force constraints with logical variables. An MLD model is used in the approach to uniformly represent the dynamic model and system constraints. The numerical simulation results indicate that DHMPC significantly improved various evaluation indicators compared to DMPC controller. The Root Mean Square values of vehicle body vertical acceleration, pitch angular acceleration and roll angular acceleration improve by 3.9%, 1.0% and 1.3%, respectively. The eccentricity of the left-rear hub-motor improve by 0.8%.
UllahSHayatRZebK, et al. Super-twisting sliding mode controller for energy storage system of a novel multisource hybrid electric vehicle: simulation and hardware validation. Int J Hydrogen Energy2024; 71: 952–963.
2.
RobertCRaveyAPereyR, et al. Global warming potential and societal-governmental impacts of the hydrogen ecosystem in the transportation sector. Int J Hydrogen Energy2024; 66: 55–65.
3.
ZhaoPPanZ. Optimisation of electric vehicle with the in-wheel motor as a dynamic vibration absorber considering ride comfort and motor vibration based on particle swarm algorithm. Proc IMechE, Part K: J Multi-body Dynamics2023; 237(1): 49–59.
4.
JinXWangJHeX, et al. Improving vibration performance of electric vehicles based on in-wheel motor active suspension system via robust finite frequency control. IEEE Trans Intell Transp Syst2023; 24(2): 1631–1643.
5.
DengZLuoXLiaoX, et al. Analysis and suppression of the negative effect of electromagnetic characteristics of wheel hub motor drive system on vehicle dynamics performance. J Veh Dyn2024; 113: 4425–4445.
6.
LiJKangSDengJ. Design and parameter optimization of a new type in-wheel motor drive electric vehicle vibration reduction system. J Vibroeng2024; 26(2): 401–413.
7.
ZhouSMaCZhangN, et al. Prediction and diagnosis for unsteady electromagnetic vibroacoustic of IPMSMs for electric vehicles considering rotor type skewing and current harmonics. J Vib Eng Technol2024; 12: 821–836.
8.
ChenXWangJHuJ, et al. An analytical model of unbalanced magnetic pull for PMSM used in electric vehicle: numerical and experimental validation. Int J Appl Electromagn Mech2017; 54(4): 583–596.
9.
ZuoSLiuZHuS. Influence of rotor eccentricity on radial electromagnetic force characteristics in switched reluctance motors and compensation. Electr Power Compon Syst2020; 48(4–5): 388–398.
10.
HochreiterSSchmidhuberJ. Long short-term memory. Neural Comput1997; 9(8): 1735–1780.
11.
WuJWangZHuY, et al. Runoff forecasting using convolutional neural networks and optimized bidirectional long short-term memory. Water Resour Manag2023; 37(2): 937–953.
12.
ElazizMAZayedMEAbdelfattahH, et al. Machine learning-aided modeling for predicting freshwater production of a membrane desalination system: a long-short-term memory coupled with election-based optimizer. Alex Eng J2024; 86: 690–703.
13.
LongGDingFZhangN, et al. Regenerative active suspension system with residual energy for in-wheel motor driven electric vehicle. Appl Energy2020; 260: 114180.
14.
WuHZhengLLiY. Coupling effects in hub motor and optimization for active suspension system to improve the vehicle and the motor performance. J Sound Vib2020; 482: 115426.
15.
WeiCHanL. Study on modeling and control for a novel active suspension. Int J Automot Technol2024; 25: 533–546.
16.
PatraAKAgrawalRDebnathMK, et al. Vehicle suspension control using LQR technique. In: 2023 IEEE 3rd international conference on sustainable energy and future electric transportation (SEFET), Bhubaneswar, India, 9–12 August 2023, pp.1–6. New York: IEEE.
17.
RobertJJKumarPSNairST, et al. Fuzzy control of active suspension system based on quarter car model. Mater Today Proc2022; 66: 902–908.
18.
KhanOEl MistriMRiveraDE, et al. A Kalman filter-based hybrid model predictive control algorithm for mixed logical dynamical systems: application to optimized interventions for physical activity. In: 2022 IEEE 61st conference on decision and control (CDC), Cancun, Mexico, 6–9 December 2022, pp.1–6. New York: IEEE.
19.
NodoziISanfeliceRG. A mixed integer approach to solve hybrid model predictive control problems. In: 2022 IEEE 61st conference on decision and control (CDC), Cancun, Mexico, 6–9 December 2022, pp.1–6. New York: IEEE.
20.
JungHOhTHParkHM, et al. Hybrid model predictive control for hybrid electric vehicle energy management using an efficient mixed-integer formulation. IFAC Pap OnLine2022; 55(7): 501–506.
21.
ChenJLinCLiangS. Mixed logical dynamical model-based MPC for yaw stability control of distributed drive electric vehicles. Energy Procedia2019; 158: 2518–2523.
22.
HuQLuWJiangJ. Dynamic modeling and adjustable damping layered control of air suspension hybrid system. Aust J Mech Eng2022; 20(1): 1–13.
23.
WèiHZhangKZhangH, et al. Resilient and constrained consensus against adversarial attacks: a distributed MPC framework. Automatica2024; 160: 111417.
24.
WangZChenSWangZ, et al. Nonlinear dynamic characteristics of ceramic motorized spindle considering unbalanced magnetic pull and contact force effects. J Braz Soc Mech Sci Eng2024; 46(3): 119.
25.
MoSChenKZhangY, et al. Vertical dynamics analysis and multiobjective optimization of electric vehicle considering the integrated powertrain system. Appl Math Model2024; 131: 33–48.
26.
KongXAbdelkarimAALiuX, et al. Stable feedback linearization-based economic MPC scheme for thermal power plant. Energy2023; 268: 126658.
27.
JiangHWangCLiZ, et al. Hybrid model predictive control of semiactive suspension in electric vehicle with hub-motor. Appl Sci2021; 11(1): 382.
28.
XuXJiangXChenL, et al. Semi-active control of a new quasi-zero stiffness air suspension for commercial vehicles based on event-triggered H∞ dynamic output feedback. Nonlinear Dyn2023; 111(13): 12161–12180.
29.
WeiHZhangHKamalA-H, et al. Ensuring secure platooning of constrained intelligent and connected vehicles against byzantine attacks: a distributed MPC framework. Engineering2024; 33: 35–46.
30.
LiZLiuCSongX, et al. Vibration suppression of hub motor electric vehicle considering unbalanced magnetic pull. Proc IMechE, Part D: J Automobile Engineering2021; 235(12): 3185–3198.
