Research On Neural Network Adaptive Control Of Nonlinear Active Suspension System

With the continuous improvement of people’s living standards,as the main carrier of road traffic,the number of cars is increasing year by year.At the same time,accompanied by the road traffic safety and environmental pollution and other problems are also increasing,and the increase of these problems has seriously threatened people’s travel safety and the sustainable development of the automobile industry.The suspension system,as the a force transmission device between the car body and the wheel,is mainly composed of three parts:elastic element,vibration damping device and guide mechanism.It can be said that the suspension system directly determines the overall performance of the car.Therefore,the control and performance evaluation of active suspension has become a hot issue in the control field.In this paper,the study of intelligent control method is carried out considering the characteristics of suspension system,such as uncertainty,time-varying and constraint characteristics.It mainly studies the following two aspects:(1)An adaptive sliding mode control scheme is developed for a class of uncertain quarter vehicle active suspension systems with time-varying vertical displacement and speed constraints,in which the input saturation is considered.The unknown items in the system are modeled by using neural networks,and the actual controller is designed under the framework of backstepping technology.The integral terminal sliding mode control algorithm is adopted to improve the convergence accuracy and avoid singularity.By constructing the corresponding Barrier Lyapunov function,the time-varying state constraints are guaranteed not to be violated.The continuous differentiable asymmetrical saturation model is established to overcome the influence of input saturation and improve the stability of the system.The stability of the system is analyzed based on Lyapunov stability theory.Finally,the simulation results show the effectiveness of the proposed control strategy.(2)An adaptive sliding mode control scheme is proposed for a class of half-car active suspension systems with prescribed performance.In order to ensure the transient and steady response of the suspension system,the vertical displacement and pitch angle of the suspension system are limited by the prescribed performance function.The terminal sliding mode control method with strong robustness is used to make the system converge quickly in a finite-time when it is far from the equilibrium point,solve the singularity problem in the control process,and reduce the chattering phenomenon of traditional sliding mode control.Neural network approximation theory deals with unknown terms in controllers.The stability of closed-loop system is analyzed based on Lyapunov stability theory.Finally,the feasibility and effectiveness of the proposed control scheme are verified by simulation comparison.