Energy management strategy for HEV based on KFCM and neural network

摘要

Aiming at the deficiency of optimal control energy management strategy, a model of energymanagement controller for hybrid electric vehicle (HEV) is constructed based on Kernel FuzzyC-means Clustering (KFCM) andmulti-neural network. Using energy management control strategybased on PMP, the operational parameters of the four driving modes for HEV is extracted;the data cluster corresponding to the drivingmode is generated by clustering through the KFCMmethod and is used as the training samples for the feedforward neural network. Taking the batterySOC, needed power and speed as the inputs of neural network, and taking engine power as theoutputofneuralnetwork, four sub-neural network models are established.Taking the vehicledrivingneeded power at the current moment and the engine output power at the previous momentas characteristic parameters, the corresponding sub-neural network model is selected for outputprediction according to the proportional relationship between the driving demand torque andthe engine output power. The simulation results show that, compared with the energy managementstrategy based onPMP, the calculation time is greatly shortened using the proposed controlstrategy, and the real-time performance is better. The fuel economy is a little decreased under thecondition of meeting the requirements, but better dynamic performance can be obtained.