@ARTICLE{Li_Chen_Design_2026,
 author={Li, Chen and Zhang, Junjiang and Ge, Shuaishuai and Liu, Mengnan and Xu, Liyou and Yan, Xianghai},
 volume={74},
 number={4},
 pages={e158771},
 journal={Bulletin of the Polish Academy of Sciences Technical Sciences},
 howpublished={online},
 year={2026},
 abstract={To address the problem of reduced comfort caused by vehicle tilt for tractor drivers in hilly terrain, a novel seat posture omnidirectional levelling system is designed, and an omnidirectional rapid levelling control strategy (QBP-PID) is proposed, which fuses Q-learning, back propagation (BP) neural network, and proportional-integral-derivative (PID) control. Firstly, an omnidirectional levelling system for seat posture is designed based on kinematic principles. On this basis, a model for the omnidirectional levelling system is established using valve-controlled hydraulic cylinder principles. Subsequently, addressing the challenge of difficult parameter tuning for the levelling system’s PID control, a multi-level parameter update strategy employing QBP-PID is proposed for rapid omnidirectional levelling control. Simulation results show that under QBP-PID control, the 15◦ lateral levelling time is 2.98 s with an overshoot of 0.32◦ ; meanwhile, longitudinal levelling time at 20◦is 3.41 s with an overshoot of 0.95◦. Compared to BP-PID and PID, lateral levelling time is reduced by 18.13% and 27.66%, respectively, while longitudinal levelling time decreases by 17.63% and 31.6%, respectively. The superiority of the QBP-PID omnidirectional rapid levelling control strategy is thus demonstrated.},
 title={Design and rapid levelling control strategy of omnidirectional levelling system for tractor seat in hilly and mountainous terrain},
 type={article},
 URL={http://www.journals.pan.pl/Content/138815/PDF/BPASTS-05485-EA.pdf},
 keywords={seat posture, omnidirectional levelling, back propagation neural network, Q-learning},
}