Search

The economical and safe energy management strategy (EMS) is essential for a battery electric vehicle (BEV). With an improved deep deterministic policy gradient (DDPG)-based EMS proposed for a dual-motor BEV, energy consumption and electric component aging are minimized. Firstly, this study incorporates health awareness of electric components into EMS. Then, this study employs a gated recurrent unit (GRU) as well as a self-attention (SA) mechanism for improving the original DDPG's performance. The GRU enhances the performance of DDPG agents, post-convergence, by furnishing them with additional state information. The SA mechanism empowers agents to distinguish the importance of state information, thus improving its adaptability in new environments. The proposed EMS decreases battery energy consumption to 7.95 kW-hour and enhances battery state of health (SOH) to 96.83 % of the dynamic programming (DP)-based EMS. The two motors of the proposed EMS possess the highest end-value SOH, i.e., 99.99929 % and 99.99978 %, respectively. The proposed EMS demonstrates superior adaptability to other EMSs, regardless of the initial state of charge (SOC). It shows the best adaptability at an initial SOC of 0.6, and achieves 95.87 % and 94.67 % of the energy consumption of DP-based EMS in the mixed and actual test cycles, respectively. • The health awareness of multiple electric components is embedded in EMS. • The GRU is employed to improve the performance of the EMS after convergence. • The Self-attention mechanism is adopted to improve the adaptability of EMS. • The proposed EMS outperforms the other EMSs in both training and testing cycles. [ABSTRACT FROM AUTHOR]

Energy management strategies (EMSs) ease mileage anxiety and improve the health performance of battery electric vehicles (BEVs). This study proposes a soft actor-critic (SAC)-based EMS for dual-motor two-speed BEV to minimize electrical energy consumption and battery capacity losses. In addition, two optimization tricks are employed to optimize the original SAC. The linear mapping trick is integrated into the actor-network of SAC to enable agents to search for optimal EMS in a discrete (driving mode)-continuous (torque distribution) hybrid action space. The SAC-based EMS is modeled as a partially observable Markov decision process (POMDP) to obtain more information about the real state of the environment. Based on this, another optimization trick, the long short-term memory (LSTM) network, is integrated into the actor and critic of SAC to make full use of both historical and current environmental information. Simulation results show that the proposed method learns the optimal EMS, its converged episodes are shortened to the 97th, the health performance of the battery is the closest to the dynamic programming (DP)-based EMS, and maintains battery operating at a range of 30–40 ° C. In addition, the proposed EMS has the best adaptability in test cycles, reaching 99.42% and 99.29% of DP-based EMS, respectively. • The EMS is modeled as a partially observable Markov decision process. • Linear mapping trick is adopted to handle the discrete-continuous hybrid actions. • A recurrent actor-critic network with memory function is proposed based on LSTM. • The proposed EMS is evaluated by comparing different EMSs under training cycle. • The proposed EMS possesses the best adaptability under test cycles. [ABSTRACT FROM AUTHOR]

Energy management strategies (EMSs) ease mileage anxiety and improve the health performance of battery electric vehicles (BEVs). This study proposes a soft actor-critic (SAC)-based EMS for dual-motor two-speed BEV to minimize electrical energy consumption and battery capacity losses. In addition, two optimization tricks are employed to optimize the original SAC. The linear mapping trick is integrated into the actor-network of SAC to enable agents to search for optimal EMS in a discrete (driving mode)-continuous (torque distribution) hybrid action space. The SAC-based EMS is modeled as a partially observable Markov decision process (POMDP) to obtain more information about the real state of the environment. Based on this, another optimization trick, the long short-term memory (LSTM) network, is integrated into the actor and critic of SAC to make full use of both historical and current environmental information. Simulation results show that the proposed method learns the optimal EMS, its converged episodes are shortened to the 97th, the health performance of the battery is the closest to the dynamic programming (DP)-based EMS, and maintains battery operating at a range of 30–40 ° C. In addition, the proposed EMS has the best adaptability in test cycles, reaching 99.42% and 99.29% of DP-based EMS, respectively. • The EMS is modeled as a partially observable Markov decision process. • Linear mapping trick is adopted to handle the discrete-continuous hybrid actions. • A recurrent actor-critic network with memory function is proposed based on LSTM. • The proposed EMS is evaluated by comparing different EMSs under training cycle. • The proposed EMS possesses the best adaptability under test cycles. [ABSTRACT FROM AUTHOR]