Research On The Model Of Flexray Adaptive Control System In Vehicle Network

At present,the automotive industry is developing at a rapid pace,and the vehicle network control technology is becoming more and more mature.There are advanced driverless cars and intelligent networked cars.Therefore,the number of on-board control units inside the car is bound to increase.It is difficult to meet the requirements of current automotive development by using traditional CAN bus,LIN bus,etc.to realize the reception,transmission and processing of large data volume in the vehicle network,so it has higher transmission rate,stronger fault tolerance performance and more flexible topology selection.And the new protocol bus FlexRay bus with event triggering and time triggering characteristics came into being,which satisfies the development requirements of the current vehicle bus.The FlexRay bus network can realize reliable,real-time and efficient information transmission between electrical units and mechanical and electronic components,ensuring the development of new automotive network technologies in the future,and has become the communication standard for next-generation in-vehicle network systems.It will lead the development of in-vehicle network systems for a long time,so it is in line with the trend of the times to study the FlexRay bus network.The FlexRay in-vehicle network control system is a fairly complex distributed control system consisting of multiple sensors,controllers,actuators and some electrical equipment.Complex and variable control tasks share network bandwidth resources in a time-multiplexed manner.However,due to the irregularity of data traffic changes in the network and the limited network bandwidth resources,data transmission instability and data delay may occur.Therefore,the control performance and stability of the system in the FlexRay network are reduced when transmitting data,and the safe and stable operation of the vehicle network control system cannot be guaranteed.This paper comprehensively considers the influence of control and scheduling on the reliability and stability of the vehicle network.From the perspective of improving the stability and reliability of the vehicle FlexRay vehicle network control system,a neural network-based adaptive control system model is designed.At present,the working state of the vehicle-mounted network,predicting the operating state of the network at the next moment,and adaptively adjusting the workload of the task online to adapt to the dynamically changing load in the vehicle network,mainly studied as follows:Firstly,the transmission mechanism of FlexRay protocol is analyzed,the network resource utilization of FlexRay vehicle network is mathematically modeled,and the nonlinear operator in the model is specially processed to simplify the solution process of the optimal solution of effective data length.Then,the neural network prediction model is established for the network resource utilization of the vehicle network,and the actual data is used for training and testing to determine the optimal number of hidden layer neurons.The performance of several common adaptive training algorithms is analyzed and compared.The trainlm algorithm trains the neural network predictive control model,and then designs a neural network predictive control system based on the FlexRay network bandwidth utilization model.Finally,the Matlab\simulink simulation tool is used to establish the experimental simulation model of the FlexRay vehicle network control system.The effectiveness and usability of the adaptive control system model is verified by simulation.