Jin, Tian, Wang, Yufeng, Ming, Wenlong ORCID: https://orcid.org/0000-0003-1780-7292, Lüdtke, Ingo, Lewis, Adam and Wang, Sheng ORCID: https://orcid.org/0000-0002-2258-2633 2024. AI-driven design approach for dual active bridge converters with increased explainability. Presented at: 13th International Conference on Power Electronics, Machines and Drives (PEMD 2024), Nottingham, UK, 10-13 June 2024. Proceedings of 13th International Conference on Power Electronics, Machines and Drives. IET Digital Library, pp. 329-336. 10.1049/icp.2024.2175 |
Abstract
The use of bidirectional on-board chargers brings significant advantages to electric vehicle (EV) charging systems. These enable high-efficiency bidirectional energy transfer, providing more flexibility for energy management and grid interconnection. Dual active bridge (DAB) converters can be used as a key component in the charging system, targeting excellent power density and high efficiency. Artificial intelligence (AI) can be used for multi-objective optimisation of DAB converters to achieve fast and accurate design. However, AI design processes have a black-box nature, and thus remain controversial for many industry applications. This article presents an explainable multi-objective optimal design framework to enable fast and accurate design with explainable artificial intelligence (XAI) for designers to enhance transparency and understanding in the decision-making process. This framework aims to provide a structured approach for including explainability in the design process, empowering designers to make informed and interpretable decisions throughout the AI-driven design phases.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Date Type: | Publication |
Status: | Published |
Schools: | Engineering |
Publisher: | IET Digital Library |
ISBN: | 978-1-83724-121-7 |
Last Modified: | 02 Sep 2024 11:30 |
URI: | https://orca.cardiff.ac.uk/id/eprint/171650 |
Actions (repository staff only)
Edit Item |