Vehicle suspension system model prediction control method based on road condition monitoring

Abstract

The invention provides a vehicle suspension system model prediction control method based on road condition monitoring, and the method comprises the steps: taking random road condition data and random control signals as the input of an active suspension system model, and taking the discrete state of the system as the output, thereby generating a large amount of training data in an offline manner to train a neural network model; a mechanism model of an active suspension system can be approached with high precision; the trained neural network model replaces a mechanism model of the active suspension system, road condition monitoring data given by the laser radar and a feasible solution of the minimization problem are used as neural network model input, and a discrete predicted value of the system state is calculated and used for solving the minimization problem, so that the minimum problem is solved. Therefore, an optimal control signal is obtained to control the electric hydraulic system to generate corresponding control force to keep the vehicle body stable. Compared with direct use of a mechanism model, the neural network model can play the advantages of relatively high nonlinear approximation capability and rapid calculation capability, so that high-speed operation and high-frequency implementation control of model prediction control are realized.

Description

technical field [0001] The invention relates to the technical field of vehicle suspension systems, in particular to a model predictive control method for vehicle suspension systems based on road condition monitoring. Background technique [0002] In today's rapid development, people's use of vehicles is gradually increasing, and passengers have higher and higher expectations for the comfort of vehicles. For improving the passenger experience, vibration reduction is undoubtedly an essential link. The suspension system is an important part of the bottom structure of the car. Its main function is to carry the dynamic load of the car body, reduce the vibration impact of the road surface uneven excitation on the car body, and try to maintain good contact between the tire and the road surface to improve the performance of the vehicle. Therefore, the optimization research of the suspension system can effectively improve the comfort, stability and safety of the vehicle, which provi...

AI Technical Summary

Problems solved by technology

From the perspective of the mechanism model of the active suspension system, the number of differential equations is large and the degree of nonlinearity is obvious. Therefore, using the mechanism model of the active suspension to predict the future system state will inevitably bring a large amount of calculation.

Images