Optimal energy management strategy of a novel hybrid dual-motor transmission system for electric vehicles

To improve the performance of powertrain configuration and heuristic strategy used in electric commercial vehicles currently for complex traffic scenarios, we propose a blended optimal rule extraction method for a novel hybrid dual-motor transmission (hDMT) system. Dynamic programming (DP) is applied to determine the optimal working points on the real-world cycles. However, it is challenging to extract online rules in real-time due to overlapping working points induced by compound running conditions. To create a trade-off between optimum and practicability, a novel blended optimal rule extraction method of energy management strategy is proposed for the integrated powertrain system. To be specific, DP is applied offline to find optimal working points from compound running scenarios. Then, a self-organizing feature map (SOM) is utilized to classify overlapped working points with reference to the characteristics of sample points. To solve the over-classification issue, the recursive k-means method is used to cluster the best matching unit generated by SOM. Based on the above, the optimal strategy is developed systematically and implemented online. Furthermore, the hardware-in-the-loop experiments and simulation results demonstrate that the proposed powertrain configuration and method can improve the economic performance of EVs. The online performance of the blended optimal strategy is highly consistent with the simulation, which can reduce energy consumption by 29.02% compared to the preliminary strategy. Compared with traditional powertrain configuration, the hDMT system also has better energy-saving potential.