Research On DCT Adaptive Shift Points Based On Driving Style Recognition

Dual-clutch automatic transmission(DCT)has been widely used for its good performance in fuel economy,power performance and ride comfort.DCT related control technology has become a hot research area.Currently,shift strategy that based on driver-vehicle-road consideration is gaining much attention,it takes the driver’s driving intention,vehicle condition,road conditions into account,so it can make the car intelligent and adaptable,but driving style,which is also a very important factor,has not been sufficiently studied.This paper presents research on DCT shift schedule based on driving style recognition,which will identify the driver’s driving style and optimize the DCT shift curves.In this thesis,the current research status on DCT development,automatic transmission shift strategy and driving style have been introduced.Then,the research has been carried out in the following aspects:First,based on working principal of cars with the automatic transmission,vehicle power transmission systems model is established,including powertrain system model,control system model,and driver model.Real vehicle testing is conducted to verify the correctness of the model.Secondly,this paper analyzes the feature data that indicating driving style,choses each accelerator pedal control cycle as the calculation period,mean opening value of accelerator pedal,mean square deviation of accelerator pedal,and mean speed of vehicle in each period as the feature parameter of driving style.Data acquisition program is designed to collect driver’s driving data of different driving style,and the data got are pretreated.Then,classification principle of the support vector machine(SVM)classifier are introduced,and with the use of cross-validation,radial basis function which is with best classification accuracy is chosen as SVM kernel function.Genetic algorithm is applied to get the best penalty factor parameter C and kernel parameter g,and the recognition accuracy of the test samples is improved.To get more robust and accurate identification of the driving style,the paper also applied the moving average method synthesize the driving style data.Finally,based on the basic shift curve,this paper studies a coordinating type of shift strategy,this shift schedule considers the economy and dynamics of the car,and adapts to different driving styles.The simulation and analysis of coordinating type of shift schedule is conducted,verifying that coordinating type shift schedule has the ability to adapt to driving style,and has are good practical value.This article takes driving style into considerations for intelligent car shifting,providing some reference value for research on improving car’s adaptation to driver.