Machine Learning Methods for Feedforward Power Flow Control of Multi-Active-Bridge Converters

• Published in: IEEE transactions on power electronics Vol. 38; no. 2; pp. 1 - 17
• Main Authors: Liao, Mian, Li, Haoran, Wang, Ping, Sen, Tanuj, Chen, Yenan, Chen, Minjie
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.02.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Active control; Artificial intelligence; Artificial neural networks; Circuits; Electric converters; Feedforward control; Flow control; Machine learning; machine-learning-in-the-loop; Model accuracy; multi-active-bridge converter; neural network; Neural networks; Power flow; power flow control; transfer learning
• ISSN: 0885-8993; 1941-0107
• DOI: 10.1109/TPEL.2022.3215459

Controlling the multiway power flow in a multi-active-bridge (MAB) converter is important for achieving high performance and sophisticated functions. Traditional feedforward methods for MAB converter control rely on precise lumped circuit models. This paper presents a machine learning (ML) method for feedforward power flow control of a MAB converter without a precise circuit model. A feedforward neural network (FNN) was developed to capture the non-linear characteristics and predict the phases needed to achieve the targeted power flow. The neural network was trained with a large amount of data, collected with a set of known phase angles. This trained network was used to predict the phases to achieve the targeted power flow. A 6-port MAB converter was built and tested to validate the methodology and demonstrate the "machine-learning-in-the-loop" implementation. Transfer learning was proven to be effective in reducing the size of the training data needed to obtain an accurate ML model. ML-based feedforward power flow control can achieve comparable accuracy as traditional model-based methods, and can function without a precise lumped circuit element model of the MAB converter.