IEEE Trans Cybern. 2022 Mar;52(3):1881-1890. doi: 10.1109/TCYB.2020.3001581. Epub 2022 Mar 11.
The adaptive neural-network (NN) output-feedback control problem is investigated for a quarter-car active suspension system. The sprung mass and the suspension stiffness in the considered suspension system are unknown, and the part states are not measured directly. In the control design, NNs are employed to approximate the unknown nonlinear dynamics, and an NN state observer is given to estimate the immeasurable states. By using the adaptive backstepping control design technique and introducing the command filter method, an observer-based NN output-feedback control algorithm is developed, in which the input saturation constraint is compensated via constructing an auxiliary system. It is proved that all the variables of the controlled system are bounded, and the ride comfort, ride safety condition, and suspension space limit are guaranteed. The computer simulation and compared results further show the effectiveness of the proposed control algorithm.
针对主动悬架系统的四分之一车模型，研究了自适应神经网络（NN）输出反馈控制问题。在所考虑的悬架系统中，簧载质量和悬架刚度未知，部分状态也无法直接测量。在控制设计中，采用神经网络逼近未知的非线性动力学，并给出神经网络状态观测器来估计不可测状态。通过自适应反步控制设计技术，并引入命令滤波方法，开发了一种基于观测器的神经网络输出反馈控制算法，其中通过构建辅助系统来补偿输入饱和约束。证明了控制系统的所有变量都是有界的，并保证了乘坐舒适性、行驶安全性和悬架空间限制。计算机仿真和对比结果进一步验证了所提出控制算法的有效性。
