Research on Braking Performance Prediction and Torque Control of Hydrodynamic Retarder Considering Temperature

In order to realize the stable control of braking torque of hydrodynamic retarder, a torque prediction and rule adaptive control method considering oil temperature is proposed. First, on the basis of analyzing the influence of oil temperature change on the braking torque, the test data set under different speed and temperature conditions is obtained. Aiming at the problem that the braking torque of real vehicle is difficult to be measured, the prediction model of the braking torque is constructed by using BP neural network and linear interpolation method, and then the real-time estimated torque of the hydrodynamic retarder is obtained. Secondly, according to the braking characteristics of the hydrodynamic retarder, a rule-based braking torque control strategy in different temperature ranges is established to realize adaptive real-time torque control in a wide temperature range. Finally, the braking torque control experiments under various working conditions are carried out. The experimental results show that the neural network prediction model of braking torque considering temperature has high accuracy, and the maximum error between the predicted value of the model and the actual braking torque value is 3.97%. Moreover, compared with the traditional PID control, the control strategy proposed in this paper improves the response speed and control accuracy of the braking torque of the hydrodynamic retarder.