Search

Aim to improve the power efficiency of the dual-active-bridge (DAB) dc–dc converter, an efficiency optimization scheme with triple-phase-shift (TPS) modulation using reinforcement learning (RL) is proposed in this article. More specifically, the Q-learning algorithm, as a typical algorithm of the RL, is applied to train an agent offline to obtain an optimized modulation strategy, and then the trained agent provides control decisions online in a real-time manner for the DAB dc–dc converter according to the current operating environment. The main objective is to obtain the optimal phase-shift angles for the DAB dc–dc converter, which can achieve the maximum power efficiency by reducing the power losses. Moreover, all possible operation modes of the TPS modulation are considered during the offline training process of the Q-learning algorithm. Thus, the cumbersome process for selecting the optimal operation mode in the conventional schemes can be circumvented successfully. Based on these merits, the proposed efficiency optimization scheme using the RL can realize the excellent performances for the whole load conditions and voltage conversion ratios. Finally, a 1.2-KW prototyped is built, and the simulation and the experimental results demonstrate that the power efficiency can be improved by using the optimization scheme based on the RL.

In recent years, resonant converters have been widely used in the fields of electric vehicles and renewable energy systems due to their excellent characteristics in terms of high energy density, high energy efficiency, wide output range, and wide ZVS range. Conventional resonant converters generally adopt pulse frequency modulation (PFM) in a wide range of output applications. This means the frequency varies over a wide range, which results in problems such as high switch loss, large noise, and high EMI. To solve this problem, this paper proposes a hybrid fixed-frequency modulation strategy applied to a wide range of outputs based on the series resonant converter, where asymmetrical voltage-cancellation control (AVC control) and its improved strategy (IAVC control) are applied in the normalized gain ranges of [0.5, 1] and [0, 0.5]. The proposed modulation strategy achieves lower switching loss, higher efficiency, and better ZVS characteristics in wide voltage output and load ranges. Under the same output voltage and power, to realize ZVS, the proposed hybrid modulation has a smaller switching frequency and resonant current, which improves efficiency and reduce losses, especially in the case of low voltage gain and light load conditions. Finally, experimental data obtained from an 80 V input and a 800 W power max prototype circuit are included to verify the proposed hybrid modulation strategy.