Smart Control of DCT Proportional Solenoid Valve Based on Data Mining

High performance of clutch control is essential for dual-clutch transmission (DCT) system to ensure good shifting smoothness of vehicle driving. The control performance of clutch in DCT driven by proportional solenoid valve depends on the output pressure control of the solenoid valve, while the output pressure of the solenoid valve is directly controlled by the energized current. Therefore, the relationship between working current and output pressure of the solenoid valve has significant impact on the clutch control and affects driving performance of the vehicle accordingly. However, the pressure-to-current (P/I) relationship of proportional solenoid valve has nonlinear hysteresis characteristic caused by magnetic materials, oil viscous friction, operation temperature, etc., which has negative effects on the accuracy and stability of solenoid valve pressure control. To cope with this problem, a machine learning model called long short-term memory (LSTM) for P/I of solenoid valve based on data mining is adopted in this paper, which is then used as feedforward compensation for closed-loop control of solenoid valve. The test result demonstrates that the machine learning model can effectively predict the output pressure at rising and falling phase of the same working current. Besides, this smart control method which has better applicability in engineering can effectively improve the control performance of proportional solenoid valve and further improve clutch control and vehicle driving performance.