Model-Predictive Control With Parameter Identification for Multi-Dual-Active-Bridge Converters Achieving Accurate Power Balancing

Dual-active-bridge (DAB) converters are widely used in power conversion systems as interfaces. To operate under high-power, high-voltage, or high-current conditions, systems constructed by multiple series-parallel DAB modules are promising solutions. Model-predictive control (MPC) is suitable for controlling complex structures such as multiple DAB converters, as it offers advantages, such as ease of multiobjective optimization, simple controller parameter design, and ease of expansion, and shows excellent dynamic performance. However, MPC applied to multiple DAB converters cannot precisely achieve target tracking and power balancing due to its high dependence on model accuracy. In this article, we investigate all four types of connections of multiple DAB modules with corresponding MPC schemes, focusing on both the single and multiple DAB modules. We analyze the errors of output voltage and power distribution caused by mismatches between model and circuit parameters. Based on this analysis, we propose integrating a recursive least squares algorithm into MPC to control multiple DAB modules and achieve accurate real-time identification of key parameters. This approach significantly improves the output accuracy and the power-balancing ability under MPC with parameter mismatches, without adding extra cost. Finally, we demonstrate the effectiveness of our proposed method through experimental platforms built to show the impact of parameter mismatches of multiple DAB modules under MPC. Our results validate the ability of the proposed approach to: 1) achieve satisfactory dynamic performance; 2) precisely track the control target; and 3) accurately balance the power of each module even under parameter mismatch conditions.