Abstract:

Vehicle velocity is a challenging research because vehicle velocity is influenced by various factors such as driving style, driving pattern, traffic condition. An accurate vehicle velocity prediction is of great significance to energy consumption research of electric vehicle. In addition, vehicle velocity prediction plays an important role in intelligent transportation system. However, vehicle velocity prediction is complicated due to the uncertainty of vehicle velocity and driving pattern. To address the challenges, a vehicle velocity prediction model based on driving pattern recognition (DPR) and Markov Chain (MC) is proposed. Firstly, three typical driving cycles are adopted to construct sample driving cycle. K-means algorithm is used for clustering the constructed driving cycle segments. Learning Vector Quantization (LVQ) neural network (NN) is applied to recognizing the driving pattern in real-time, then the Markov Transition Matrix (MTM) corresponding to three clustered driving patterns are adopted to predict vehicle velocity. Finally, the velocity prediction results are applied to dual-motor EV energy consumption evaluation model which is established by Multiple Linear Regression (MLR). Velocity prediction results show that the Root Mean Square Error (RMSE) value of velocity prediction based on DPR and MC decreased by 24.1% compared with MC prediction without DPR. The velocity prediction is applied to energy consumption evaluation, the results shows that the error is 2.33%, which is sufficient to demonstrate the accuracy of the velocity prediction model and the energy consumption evaluation model. In real-time prediction part, the corresponding MTM is invoked to predict the future vehicle velocity according to the recognition results of LVQNN.