Energy active adjustment and bidirectional transfer management strategy of the electro-hydrostatic hydraulic hybrid powertrain for battery bus

Abstract

The electro-hydrostatic hydraulic hybrid (EH3) powertrain has unique advantages in efficient recovery and utilization of energy. However, it also faces severe challenges in the decision-making of active adjustment and bidirectional transfer between multiple energy sources under the influence of driving pattern. Taking battery buses as the object, the power and energy-saving characteristics of EH3 powertrain under the control of driving pattern recognition (DPR) and fuzzy logic rules (FLR) are studied in this paper. The control ideas of active adjustment and bidirectional transfer of electric power and hydraulic power guided by the results of DPR are proposed. Firstly, the driving patterns and velocity in the actual driving scene is tested, and the data is divided into multiple short driving cycles through a rolling time window. Secondly, the K-means clustering algorithm is used to classify the obtained short driving cycles. The classification results are used as samples to train and test the Learning Vector Quantization neural network (LVQ-NN) to realize online recognition and prediction of driving patterns. Finally, the FLR controller is introduced to process multiple input variables, and the results of DPR and FLR are integrated to realize the active adjustment and bidirectional transfer of electric motor (EM) and variable pump/motor. The simulation results show that compared with the traditional control strategies, energy management strategy (EMS) based on DPR and FLR can effectively realize the intelligent adjustment and transfer of energy between composite power sources, and significantly improve the driving range and service life of the battery.