Road feeling simulation method based on GMM and BP neural network

Abstract

The invention provides a road feeling simulation method based on a GMM (Gaussian Mixture Model) and a BP (Back Propagation) neural network, which comprises the following steps of: performing a real vehicle road test test and acquiring data, preprocessing test data, clustering normalized test data, dividing the data into a training data set and a test data set, training and testing a road feeling simulation model based on the GMM and the BP neural network, and judging whether the obtained road feeling model meets requirements or not; and performing road feeling simulation according to the obtained road feeling simulation model based on the GMM and the BP neural network. The input variables of the BP neural network model are the longitudinal vehicle speed, the vehicle transverse acceleration, the vehicle yaw velocity, the vehicle vertical load, the steering wheel angle and the steering wheel angular velocity, and the output variable of the BP neural network model is the steering wheel torque. Compared with the prior art, the GMM and BP neural network-based road feeling simulation model obtained by the method has obvious advantages in modeling time, precision and operation speed.

Description

technical field [0001] The invention relates to the technical field of vehicles, in particular to a road sense simulation method based on GMM and BP neural network. Background technique [0002] Steering road feel, also known as steering force feeling and steering wheel feedback torque, refers to the reverse resistance torque felt by the driver through the steering wheel feedback torque. Since this road sense can transmit important road surface information to the driver in real time, it is of great significance for the driver to make correct decisions and ensure driving safety. Therefore, for a simulated driver or a vehicle using a steer-by-wire system, generating a highly reliable road feel is one of its indispensable functions. However, there is currently no method for high-precision modeling of road feeling, because most methods are designed for mechanism modeling, and there are many parameters that need to be tuned, and there are a large number of parameters that are di...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned technical problems, the object of the present invention is to provide a kind of road feeling simulation method based on GMM and BP neural network, carry out modeling with real vehicle test data, Gaussian mixture model (GMM) classification algorithm and BP neural network algorithm, obtain The road sense simulation model based on GMM and BP neural network solves the problems of complex model structure and low precision in traditional mechanism modeling

Images