Search

The prosperous development of electric vehicles has promoted the application of interior permanent magnet synchronous motors (IPMSMs). The flux‐intensifying IPMSM has attracted more attention due to its high power‐density and better flux‐weakening performance. However, the optimisation efficiency and motor performance require further study in the actual optimisation design. To this end, this study is to optimise the electromagnetic field structure of motor rotors with the back propagation neural networks (BPNN) and multi‐objective optimisation methods. Concretely, dimensional parameters of an initial motor are extracted as optimisation variables. Then, the BPNN are utilised to stimulate the motor performance obtained with finite element methods (FEM). With the trained BPNN, FEM tools are replaced in the subsequent optimisation process, which alleviates the computational burden. Besides, to address the problem of multi‐objective optimisation with inequality constraints, the sequential unconstrained minimisation technique is incorporated into the non‐dominated sorting genetic algorithm to obtain the Pareto frontier. Finally, the optimal design point is selected from the Pareto frontier. The simulation and experiment have been implemented to verify the superiority of the optimised rotor structure. Generally, this study has laid the foundation of the following motor optimisation with the higher executability and lower computational burden.

The performance of plug-in hybrid electric vehicles (PHEV) depends on the energy management strategy (EMS). An optimal EMS guarantees the maximum use of the energy through the electric power grid, coordinates the power output of the main power sources, and exploits the comprehensive advantages of both engine and motor. However, the current EMS can not guarantee the real-time processing of the optimal allocation problem. With the rapid development of communication network technology and Internet of vehicles technology, it provides a new idea to solve the above problems, namely cloud computing. EMS based on cloud computing is divided into online cloud and offline cloud. The off-line cloud uses dynamic programming to pre distribute torque according to the expected driving conditions, while the online cloud modifies the vehicle torque based on real-time vehicle speed and road information. The simulation is carried out under the Beijing speed condition. The simulation results show that this method can make most of the working points of the engine and motor run in the high efficiency range, which verifies the effectiveness of this method.

Expanding the travel mileage of power batteries is of great significance for electric vehicles (EVs). The solar battery pack is considered as a promising supplement to the battery management system (BMS) of EVs but integrating solar power into EVs remains a challenge. This paper proposes a BMS that coordinates the solar panels and the lithium battery system. The proposed BMS mainly involves three aspects. Firstly, an equivalent second-order resistance-capacitance model is established and afterwards is identified by using an improved recursive least squares algorithm. Then, the maximum power prediction strategy is developed based on the advanced state of charge (SOC) algorithm and the available solar energy estimation algorithm. Thirdly, a multi-stage constant current charging strategy based on the adaptive genetic algorithm is designed to optimize the battery temperature rise and charging time simultaneously. The proposed BMS is validated by the experiment on a real-world solar-assisted EV. The results indicate that the proposed power prediction strategy can accurately estimate the available power for EVs. Compared with the widely-used charging method, the developed optimal charging strategy reduces the charging time and temperature rise by 7%–11% and 36%–45%, respectively.

The performance of the all-wheel-drive electric vehicle is inseparable from the energy management strategy (EMS). An outstanding EMS could extend the cycling mileage, coordinating the power output of the battery and exerts the advantage of the motor comprehensively. However, the current EMS has poor performance in real-time, and this paper proposes the dynamic programming coordination strategy (DPCS) to solve the problem. Firstly, the EMS based on a rule-based control strategy (RBCS) is applied in a different driving cycle. Secondly, the dynamic programming algorithm (DP) is proposed in the process. The DPCS cooperated the advantage of RBCS and DP, extracting the boundary parameters along with the demand power and vehicle speed. Finally, the number of motors joined in the driving condition is elucidated and the method obtains the optimal torque split ratio through a partly-known driving cycle. By incorporating the thought of a basis of rules, the DPCS determines the torque of each motor that confirm the motor working in an efficient range that incorporates the mind of dynamic programming. The method is validated through the simulation. The results show that the strategy can significantly improve the mileage of the driving cycle, with comprehensive performance in energy distribution and utilization.

With decades’ development of energy management strategy in hybrid electric vehicle, learning-based method has been deemed as a key solution for energy economy and real time. However, current energy management strategy cannot reach an optimal energy economy performance and online update in a tolerable time lag. Aiming at solving these problems, an accelerated reinforcement learning method and an online-updated strategy are proposed in present work. Firstly, prioritized replay is applied in deep Q network with normalized advantage function for a fast convergence to an optimal strategy. Prioritized replay module endows weight to trained history data which is utilized in neural network training. The neural network is updated towards optimal strategy by weight in an effective way. Secondly, the online-updated strategy for fix-line hybrid electric vehicle is designed based on the accelerated reinforcement learning method and model predictive control. The predicted future road information generated by model predictive control in each time interval is delivered to the accelerated reinforcement learning module for online energy management strategy generating. Finally, with all efforts above, the online-updated strategy is carried out and validated through hardware-in-the-loop simulation. The results show that this approach promotes the energy economic performance while updating strategy in real time.

The performance of Plug-in Hybrid Electric Vehicle (PHEV) depends on the energy management strategy (EMS). An optimal EMS guarantees the maximum use of the energy through electric power grid, coordinates power output of main power sources and exerts comprehensive advantages of both engine and motor. However, the current EMS cannot react to the dynamic driving cycles in the future and thus have a bad real-time performance. In order to solve these problems, a novel EMS based on rule-based energy strategy (RE), dynamic programming algorithm (DP) and equivalent fuel consumption algorithm (ECMS) is proposed. First, DP is used to extract the boundary of mode switching and shift schedule under three typical driving cycles in offline, especially, RE is corrected using the boundary of mode switching. Second, an instantaneous optimization strategy-ECMS is used to replace the Charge-Depleting Mode (CD) of RE for finding the real-time optimal solution in a wider range in online, in this part, owe to the fixed distance of urban public transport, a reference State of Charge (SOC) is formulated, and the Proportion-Integration (PI) algorithm is used to make the actual SOC always follow the reference SOC by adjusting the equivalent factor. Finally, combine all the above efforts, a real-time optimization EMS is proposed and validated through simulation and experiment. The results show that this approach can significantly enhance the vehicle drivability, with overall obvious improvement of the comprehensive performance qualification based on both fuel economy and drivability.