A virtual acceleration calibration method for parameters of an electric control system of a chassis based on Bayesian optimization

Abstract

The application is a virtual acceleration calibration method for parameters of a chassis electronic control system based on Bayesian optimization. The method comprises the following steps: 1. establishing an optimization objective function of the chassis electronic control system; 2. completing pre-training of a Bayesian proxy model; 3. building a high-precision simulation model of the current chassis electronic control system and a test working condition scene model in a simulation environment; 4. sampling test working condition types and test working condition specific parameters by using a Bayesian probability improvement method; 5. performing tests in the simulation environment by using the test working condition types and parameters obtained by sampling and obtaining an objective function result of the system under the working condition to be calibrated; 6. optimizing the pre-trained proxy model based on the obtained new data; and 7. performing cyclic iteration until a target condition of the virtual acceleration calibration process is reached, and obtaining the chassis electronic control system corresponding to the optimal objective function. The application can effectively solve the problem of waste of test resources caused by multi-dimensional parameter traversal combination of the chassis electronic control system and accelerate the virtual calibration process of the chassis electronic control system.

Images