An Operating Point Adjustment Model Using PMP-GWO-Bi-LSTM for RANGE Extended Electric Vehicle

The increasingly severe energy problems and environmental pollution have imposed severe requirements on the fuel saving level of vehicles. The range extender configuration is a tandem structure that has attracted more and more researchers’ attention due to its architectural features and control methods. An intelligent APU operating point adjustment model based on PMP-GWO-Bi-LSTM is proposed in this paper to enhance adaptability to real driving conditions for the traditional optimal strategy. Firstly, a PMP model has been applied into a range extended electric vehicle model from which the optimized power distribution data under several standard driving cycles was recorded as the input to deep learning model. Secondly, a Bi-LSTM model fed by control parameters and power distribution data was established and trained using aforementioned datasets. The aim is to learning the nonlinear regression relationship model between APU control variables and power distribution. Furthermore, the GWO optimization algorithm is introduced to optimize the hyperparameter of Bi-LSTM to speed up the running speed of the model and improve accuracy. Finally, the experiment was conducted using real driving condition data to predict the power distributions. The simulation results show APU overall efficiency improvement by 15.87% whilst fuel consumption improved by 9.42%. The number of hyper parameters such as the iterations and hidden layer units using GWO optimization algorithm is 35.50% and 38.38% less and the training time decreases by 4.61 s, which proves that the model proposed in this paper can achieve good result in real driving conditions.