Search

Lithium-ion batteries (LIBs) have been widely used for electric vehicles owing to their high energy density, light weight, and no memory effect. However, their health management problems remain unsolved in actual application. Therefore, this paper focuses on battery capacity as the key health indicator and proposes a data-driven method for capacity prediction. Specifically, this method mainly utilizes Convolutional Neural Network (CNN) for automatic feature extraction from raw data and combines it with the Bidirectional Long Short-Term Memory (BiLSTM) algorithm to realize the capacity prediction of LIBs. In addition, the sparrow search algorithm (SSA) is used to optimize the hyper-parameters of the neural network to further improve the prediction performance of original network structures. Ultimately, experiments with a public dataset of batteries are carried out to verify and evaluate the effectiveness of capacity prediction under two temperature conditions. The results show that the SSA-CNN-BiLSTM framework for capacity prediction of LIBs has higher accuracy compared with other original network structures during the multi-battery cycle experiments. [ABSTRACT FROM AUTHOR]

Considering the disadvantages of energy management multi- objectives optimization for hybrid electric vehicle（ HEV） which usually adopts weighted sum method,by using the Pareto optimum algorithm,based on non- dominated sorting method to deal with the fuel economy and emissions（ CO,NOxand HC） evaluation indexes,then a new adaptive differential evolution algorithm is proposed and simulated which can be applied to multi- objective optimization of HEV energy management. The simulation results show that,a Pareto optimal solution set can be obtained by the proposed multi- objectives optimization method. And the maximum fuel economy increases by 5. 30%,the largest CO emissions reduces by 3. 65%,in the biggest NOxfalls by 14.40%,the max HC drops down by 3.26%.

For the fluctuations problem of driveline torque which results from working-mode switching of dual-clutch parallel hybrid electric vehicles with integrated starter / Generator（ ISG）,focusing on study the process of transferring from pure electric working model to only engine working model.Based on the method of optimal the total efficiency of hybrid electric vehicle,the steady-state energy management control strategy is established,and then steady torque distribution area is achieved,which is the basis of coordination and control of dynamic torque.For the problem adopted the engine dynamic torque estimate genetic algorithm based on BP neural network algorithm,and ISG motor torque compensation method is proposed for dynamic torque coordinated control strategy.The simulation results show that the method proposed above can significantly decreases the torque fluctuations of working model transferring process,at the same time,the jerk to driveline is greatly reduced.

The currently existing energy management control optimization for hybrid electric vehicle (HEV) mainly focuses on fuel economy. Apart from this, there has been some consideration of the impact of emissions, but almost no attention has been paid to drivability performance. Therefore, from the point of view of multi-objectives optimization, the influences of fuel economy, emission and drivability performance on the energy management are comprehensively considered for a parallel HEV. The energy management control parameters and driveline parameters are selected to be optimized parameters. Then, the NSGA-II (Fast Non-dominated Sorting Genetic Algorithm-II) algorithm is proposed to solve the multi-objectives optimization problem. Furthermore, the multi-objectives optimization method for HEV energy management control is established and comparatively simulated with the parallel electric assist control strategy. The results show that the evaluation index of drivability decreases by 27.12% from the maximum and the average enhancement effect of optimization falls by 20.84%. The evaluation index of fuel economy declines by 22.30% from the maximum and the average index drops by 20.26%. The comprehensive index of emission performance descends by 11.33% from the maximum. The proposed multi-objectives optimization algorithm has good convergence and distribution, and obtains more Pareto optimal solution sets, which can provide more selectivity in building HEV energy management control strategies. [ABSTRACT FROM AUTHOR]