Data-Light Physics-Informed Modeling for the Modulation Optimization of a Dual-Active-Bridge Converter

In modulation optimization, power converter modeling is pivotal for performance evaluation. However, mainstream knowledge-based approaches suffer from low accuracy and heavy computation burden, while emerging data-driven methods are data-intensive and opaque black-box models. Even the state-of-the-art physics-informed artificial intelligence (AI) is improper for modulation optimization due to resource-intensive re-training for new predictions. Hence, a physics-in-architecture recurrent neural network (PA-RNN), which customizes recurrent neurons to integrate physical laws into structure, is proposed, tailoring for modulation optimization of power converters. The PA-RNN model reveals diverse circuit insights, exhibiting data-light merit and on-call prediction capability. Modulation optimization via PA-RNN involves two stages. First, PA-RNN constructs converter models in time domain for direct performance evaluation. Second, an optimization algorithm interacts with the PA-RNN model to minimize current stress while realizing full-range soft switching. Two design cases are presented: first, modeling buck converters; second, optimizing dual-active-bridge converters under a triple phase shift modulation or a five-degree-of-freedom modulation. Algorithm experiments and 1-kW hardware experiments have comprehensively validated the merits and feasibility of the proposed PA-RNN. Broadly speaking, this paper strives to increase the penetration of AI in power electronics.