Neural Network Adaptive Event Triggered Control Of Vehicle Suspension System

With the continuous improvement of people’s quality of life,people put forward higher requirements for the ride comfort,handling stability and driving safety of vehicles,and the suspension system is the key to achieve this goal.Among them,the active suspension system is widely concerned because its stiffness and damping characteristics can be adjusted adaptively according to the driving conditions.In addition,the seat suspension is the last barrier for the vehicle to alleviate vibration and improve comfort.The seat suspension and vehicle suspension system jointly improve the ride comfort,stability and driving safety.At the same time,with the intelligent of the car,the car is a complex system with multiple complex subsystems.Due to the limitations of the car,it is easy to cause the shortage of communication resources,waste,and even packet loss,which may cause serious safety accidents.How to save communication resources and avoid the effective waste of communication resources under the condition of ensuring the stability of the control system Using intelligent control method to solve the control problem of active suspension system is a research hotspot in the field of control.This paper focuses on the following two aspects;(1)An adaptive event triggered control scheme is proposed for the seat suspension system with time-varying full state constraints.Consider that communication resources may be limited,this paper proposes a dynamic relative threshold strategy to reduce the communication burden of actuator and controller.Compared with the fixed value as trigger condition,the dynamically changing thresholds as trigger conditions is more general and universal.The time-varying full state constraint problem is solved by using Barrier Lyapunov Function(tan).In addition,the radial basis function neural networks are employed to approximate the unknown terms,the designed event triggered controller can make the vertical displacement and speed of the seat suspension system close to zero,and the tracking signal can track the output of the system well.Then,all signals in the resulted system are bounded,and the Zeno behavior can be avoided successfully.Moreover,all the system states satisfy their corresponding constraint condition.Finally,the feasibility and rationality of this method are proved by the simulation analysis of a real example of seat suspension system.(2)Aiming at the electromagnetic active suspension system of vehicle,the event triggering control problem of Electromagnetic Active Suspension Based on neural network is proposed.In the design process,radial basis function neural network is used to approximate the unknown term.Aiming at the limitation of vehicle communication resources,the control schemes with fixed threshold and relative threshold are proposed to reduce the communication burden between actuator and controller.Firstly,a trigger mechanism based on fixed threshold is proposed,and the algebraic loop problem is solved by using the special properties of radial basis function neural network.Secondly,in order to further avoid large measurement error,an event triggering method based on time-varying threshold is established.The radial basis function neural network is used to approximate the position smooth function.The designed event triggering controller can make the vertical displacement and speed of the electromagnetic suspension system close to zero.Then,the Lyapunov stability analysis theory is used to prove that all signals in the system are bounded,and the Gino behavior is successfully avoided.Finally,through the simulation analysis of the electromagnetic suspension system,the feasibility and rationality of the two methods are verified.