A vehicle crosswind test method based on bp neural network control

Abstract

The invention discloses a vehicle crosswind test method based on BP neural network control, comprising the following steps: step one, according to a sampling period, the starting end electromagnetic device energizing current is Ia, the ending end electromagnetic device energizing current is Ib, the distance from a simulation device to the starting end is Da, the distance from the simulation deviceto the ending end is Db, the operating speed of the simulation device is V, and the wind speed of the crosswind test is v; step two, the above parameters are normalized, and the input layer vector xof a three-layer BP neural network is determined to be equal to {x1, x2, x3, x4, x5, x6}; step three, the input layer vector is mapped to an intermediate layer, the intermediate layer vector y is equal to {y1, y2 - ym}, wherein m is the number of intermediate layer nodes; step four, the output layer vector o is obtained to be equal to {o1, o2, o3, o4}; step five, the starting end electromagnetic device energizing current and the ending end electromagnetic device energizing current are controlled; and step six, the direction of the starting end electromagnetic device energizing current and thedirection of the ending end electromagnetic device energizing current at the No.i+1 moment are determined.

Description

technical field [0001] The invention relates to the field of vehicle testing, in particular to a vehicle crosswind test method based on BP neural network control. Background technique [0002] When the wind direction is not exactly parallel to the driving direction, the wind is said to have a crosswind component, meaning that the wind can be divided into two parts, a crosswind, and a tailwind / headwind component. Under these conditions, the vehicle behaves the same as if it were only experiencing its crosswind component. The crosswind component is the sine of the angle between the wind and the direction of travel multiplied by the wind speed, and the headwind component is calculated in the same way as the crosswind component, except using cosines instead of sines. Crosswinds can also cause trouble when driving on slippery surfaces, especially if there are momentary strong winds and the vehicle has a large side area. This is dangerous for the driver, as lift may be created, ...

AI Technical Summary

Problems solved by technology

However, neither of these two methods can accurately simulate the real situation of the car in the process of driving on the road, and it is easy to cause certain errors in the test of the car.

Images