Huang Chen, Liu Yang, Sun Xiaoqiang, Wang Yiqi
Institute of Automotive Engineering, Jiangsu University, Zhenjiang 212013, China.
Sensors (Basel). 2025 Jul 31;25(15):4723. doi: 10.3390/s25154723.
Sensor fusion in intelligent suspension systems constitutes a fundamental technology for optimizing vehicle dynamic stability, ride comfort, and occupant safety. By integrating data from multiple sensor modalities, this study proposes a hierarchical multi-sensor fusion framework for active suspension control, aiming to enhance control precision. Initially, a binocular vision system is employed for target detection, enabling the identification of lane curvature initiation points and speed bumps, with real-time distance measurements. Subsequently, the integration of Global Positioning System (GPS) and inertial measurement unit (IMU) data facilitates the extraction of road elevation profiles ahead of the vehicle. A BP-PID control strategy is implemented to formulate mode-switching rules for the active suspension under three distinct road conditions: flat road, curved road, and obstacle road. Additionally, an ant colony optimization algorithm is utilized to fine-tune four suspension parameters. Utilizing the hardware-in-the-loop (HIL) simulation platform, the observed reductions in vertical, pitch, and roll accelerations were 5.37%, 9.63%, and 11.58%, respectively, thereby substantiating the efficacy and robustness of this approach.
智能悬架系统中的传感器融合是优化车辆动态稳定性、乘坐舒适性和乘客安全性的一项基础技术。通过整合来自多种传感器模态的数据，本研究提出了一种用于主动悬架控制的分层多传感器融合框架，旨在提高控制精度。首先，采用双目视觉系统进行目标检测，能够识别车道曲率起始点和减速带，并进行实时距离测量。随后，全球定位系统（GPS）和惯性测量单元（IMU）数据的融合有助于提取车辆前方的道路高程轮廓。实施BP-PID控制策略，以制定在三种不同道路条件下（平坦道路、弯曲道路和障碍物道路）主动悬架的模式切换规则。此外，利用蚁群优化算法对四个悬架参数进行微调。利用硬件在环（HIL）仿真平台，观察到垂直、俯仰和侧倾加速度分别降低了5.37%、9.63%和11.58%，从而证实了该方法的有效性和鲁棒性。
