In this article, an adaptive neural network control system is proposed for a quarter car electrohydraulic active suspension system coping with dynamic nonlinearities and uncertainties. The proposed control system is primarily designed to stabilize a sprung mass position of the quarter car electrohydraulic active suspension. Linear controllers such as the proportional–integral–differential controller have limited control performances. The limited control performances are caused by dynamic phenomena such as nonlinearity, parametric uncertainties, and stiff external disturbances. To overcome these dynamic phenomena, we propose a combined adaptive radial basis function neural network with a backstepping control system for a quarter car active suspension system. This setup can handle the unmatched model uncertainty of the system, while the adaptive neural network can take care of its unknown smoothing functions. In general, radial basis function neural network can represent a complicated function, and therefore, semi-strict-feedback dynamic systems are considered to simplify the adaptive neural network control design. Simulation results are indicated to illustrate adaptive neural network control effectiveness.

在本文中，针对四分之一汽车电液主动悬架系统的动态非线性和不确定性，提出了一种自适应神经网络控制系统。拟议的控制系统主要用于稳定四分之一车电液主动悬架的弹簧摆放位置。线性控制器，例如比例-积分-微分控制器，具有有限的控制性能。有限的控制性能是由诸如非线性，参数不确定性和强外部干扰之类的动态现象引起的。为了克服这些动态现象，我们为四分之一汽车主动悬架系统提出了一种带有反推控制系统的组合式自适应径向基函数神经网络。此设置可以处理系统无法比拟的模型不确定性，而自适应神经网络可以处理其未知的平滑功能。通常，径向基函数神经网络可以表示复杂的函数，因此，考虑使用半严格反馈动态系统来简化自适应神经网络的控制设计。仿真结果表明了自适应神经网络控制的有效性。