To improve computational efficiency of energy management strategies for plug-in hybrid electric vehicles (PHEVs), this paper proposes a stochastic model predictive controller (MPC) based on Pontryagin's Minimum Principle (PMP), which differs from widely used dynamic programming (DP)-based predictive methods. First, short-time speed forecasting is achieved using a Markov chain model, based on real-world driving cycles. The PMP-and DP-based MPCs are compared under four preview horizons (5s, 10s, 15s and 20s), and the results show that the computational time of the DP-MPC is almost four times of that in the PMP-MPC. Moreover, the influence of predication horizon length on computational time and energy consumption is examined. Given a preview horizon of 5s, the PMP-MPC holds a total energy consumption cost of 7.80 USD and computational time per second of 0.0130 s. When the preview horizon increases to 20 s, the total cost is 7.77 USD with the computational time per second increasing to 0.0502 s. Finally, DP, PMP, and rule-based strategies are contrasted to the PMP-MPC method, further demonstrating the promising performance and computational efficiency of the proposed methodology.

No abstract

No abstract

a b s t r a c tIn order to achieve near-optimal fuel economy for plug-in hybrid electric vehicles (PHEVs) using the equivalent consumption minimum strategy (ECMS), it is necessary to dynamically tune the equivalent factor (EF). Unlike widely used model-based approaches, this paper proposes a data-driven ECMS that determines the EF using an artificial neural network (ANN). First, by comparing Pontryagin's Minimum Principle (PMP) with the ECMS, one can find that the EF is related to the co-state value of the PMP method. Then, an ANN is constructed with three accessible input variables, including the current demanded power, the ratio of the distance travelled to the total distance, and the battery State of Charge (SOC). The neural network is subsequently trained using real-world speed profiles. Simulations are performed considering different initial SOC values. The results reveal that the proposed data-driven ECMS demonstrates satisfactory fuel economy compared to global optimization methods like dynamic programming and PMP methods. The computational time of the proposed method relative to the duration of the entire trip indicates a great potential for the development of a time-conscious energy management strategy. Moreover, the impact of training sample size on the ANN performance is discussed.