Mode prediction system and method for coordinated control of power system of hybrid electric vehicle

Abstract

The invention provides a mode prediction method for hybrid electric vehicle power system coordination control. The mode prediction method comprises the following steps that a control strategy model based on model prediction control is established according to the power system configuration of a hybrid electric vehicle; establishing an LSTM neural network prediction model of the vehicle demand torque, the vehicle speed and the battery SOC based on an LSTM neural network; inputting the current driving historical data of the hybrid electric vehicle into an LSTM neural network prediction model, and outputting predicted values of the demand torque, the vehicle speed and the battery SOC of the hybrid electric vehicle after a preset time period through the LSTM neural network prediction model; and the control strategy model judges a mode that the hybrid electric vehicle is about to enter according to the predicted values and controls the hybrid electric vehicle to perform mode switching when the predicted values of the required torque, the vehicle speed and the battery SOC reach mode switching conditions. On the basis of power source coordination control, mode switching can be predicted, mode switching can be conducted in advance, the switching time is prolonged, and therefore the purpose of reducing the impact degree is achieved.

Description

technical field [0001] The invention relates to the technical field of mode switching of hybrid electric vehicles, in particular to a mode prediction system and method for coordinated control of a hybrid electric vehicle power system. Background technique [0002] With the introduction of hybrid electric vehicles (HEV) into thousands of households, the problem of coordinated control of the power system of hybrid vehicles has gradually entered people's field of vision. The operation of HEV involves the coupling between multiple power sources, and its structure is more complicated than that of traditional fuel vehicles. The working modes of the power sources in different working modes are different, and the difference in the dynamic response time of the power sources is easy to cause large changes in the mode switching process. Therefore, in order to improve the vehicle performance of hybrid electric vehicles during mode switching, it is of great research value and significanc...

AI Technical Summary

Problems solved by technology

[0004] When entering the hybrid mode, the motor MG1 will drive the engine 1 to start, and then reach the economical speed and maintain its speed at the optimum position. The engine 1 will start when it reaches the idle speed and begin to respond to the demand torque, but the torque response Compared with the motor is slower, the torque of the two motors cannot cooperate well with the torque of the engine 1 when the engine 1 is started, resulting in unstable power output and longitudinal impact on the vehicle

Images