EPE Association: EPE 2025 - LS3c: Digitalization: The powerful fusion of AI and IoT for sustainability

EPE 2025 - LS3c: Digitalization: The powerful fusion of AI and IoT for sustainability
You are here: EPE Documents > 01 - EPE & EPE ECCE Conference Proceedings > EPE 2025 - Conference > EPE 2025 - Topic 04: Digitalization: the Powerful Fusion of AI and IoT for Sustainability > EPE 2025 - LS3c: Digitalization: The powerful fusion of AI and IoT for sustainability

   [return to parent folder]

   A Virtual Platform for Modular Smart Battery Testing and Prototyping
By Francesco SIMONETTI, Roberta DI FONSO, Nicolai WEINREICH, Yusheng ZHENG, Arman OSHNOEI, Xin SUI, Remus TEODORESCU [View]
[Download]

Abstract: Developing and testing algorithms for the management and control of modular smart batteries posesevere safety problems due to the inherent risk of hazards when dealing with battery cells.This work proposes a virtual prototyping platform aiming to validate the performance of the controller without involving the use of real battery cells.This setup allows real-time tests in safety conditions, which is preliminary to the validation on the real battery system.

   Developing a Model-in-the-Loop Testbench for Battery Management Systems: Advancing Test Methodologies for State-of-X Estimation
By Iván SANZ-GORRACHATEGUI, Aitor BARRUTIA, Ana MARTÍN, Xabier ARRAZTOA-LAZKANOTEGI, David MARCOS, Peio ONAINDIA [View]
[Download]

Abstract: Lithium-ion battery systems require robust BMS for safety and reliability. Extensive BMS testing presents challenges like safety risks, long testing times, and variability. To address these issues and expedite development, a testing methodology based on X-in-the-Loop (XiL) paradigms is proposed. This methodology ensures comprehensive validation and cost reduction. Using MathWorks Simulink and Simscape Batteries, a virtual testbench is developed to model both the BMS and the battery pack. The BMS includes virtualized master and slave units, emulating sensor behavior and SoC estimation algorithms. A virtual battery cycler enables specific current profile testing. As case study, this setup benchmarks SoC estimation algorithms at MiL and SiL levels, with potential HiL expansion for real BMS device validation, enhancing testing capabilities and automating procedures for safer, faster BMS development.

   Ultrasound-based Condition Monitoring of Power Converters with Physics-Informed Compression
By Youssof FASSI, Vincent HEIRIES, Jérôme BOUTET, Julien MARIANNE, Sébastien MARTIN, Mathilde CHAREYRON, Clément CHAMBON, Sébastien BOISSEAU [View]
[Download]

Abstract: Condition monitoring of power converters is vital but challenging due to sensor invasiveness and high computational demands. This paper introduces a non-invasive ultrasound-based approach using CNN autoencoders with a physics informed loss function for efficient data compression, outperforming traditional wavelet methods, enhancing data storage needs, and improving diagnostic feature extraction.

EPE 2025 - LS3c: Digitalization: The powerful fusion of AI and IoT for sustainability
You are here: EPE Documents > 01 - EPE & EPE ECCE Conference Proceedings > EPE 2025 - Conference > EPE 2025 - Topic 04: Digitalization: the Powerful Fusion of AI and IoT for Sustainability > EPE 2025 - LS3c: Digitalization: The powerful fusion of AI and IoT for sustainability
	[return to parent folder]

	A Virtual Platform for Modular Smart Battery Testing and Prototyping By Francesco SIMONETTI, Roberta DI FONSO, Nicolai WEINREICH, Yusheng ZHENG, Arman OSHNOEI, Xin SUI, Remus TEODORESCU	[View] [Download]
Abstract: Developing and testing algorithms for the management and control of modular smart batteries posesevere safety problems due to the inherent risk of hazards when dealing with battery cells.This work proposes a virtual prototyping platform aiming to validate the performance of the controller without involving the use of real battery cells.This setup allows real-time tests in safety conditions, which is preliminary to the validation on the real battery system.

	Developing a Model-in-the-Loop Testbench for Battery Management Systems: Advancing Test Methodologies for State-of-X Estimation By Iván SANZ-GORRACHATEGUI, Aitor BARRUTIA, Ana MARTÍN, Xabier ARRAZTOA-LAZKANOTEGI, David MARCOS, Peio ONAINDIA	[View] [Download]
Abstract: Lithium-ion battery systems require robust BMS for safety and reliability. Extensive BMS testing presents challenges like safety risks, long testing times, and variability. To address these issues and expedite development, a testing methodology based on X-in-the-Loop (XiL) paradigms is proposed. This methodology ensures comprehensive validation and cost reduction. Using MathWorks Simulink and Simscape Batteries, a virtual testbench is developed to model both the BMS and the battery pack. The BMS includes virtualized master and slave units, emulating sensor behavior and SoC estimation algorithms. A virtual battery cycler enables specific current profile testing. As case study, this setup benchmarks SoC estimation algorithms at MiL and SiL levels, with potential HiL expansion for real BMS device validation, enhancing testing capabilities and automating procedures for safer, faster BMS development.

	Ultrasound-based Condition Monitoring of Power Converters with Physics-Informed Compression By Youssof FASSI, Vincent HEIRIES, Jérôme BOUTET, Julien MARIANNE, Sébastien MARTIN, Mathilde CHAREYRON, Clément CHAMBON, Sébastien BOISSEAU	[View] [Download]
Abstract: Condition monitoring of power converters is vital but challenging due to sensor invasiveness and high computational demands. This paper introduces a non-invasive ultrasound-based approach using CNN autoencoders with a physics informed loss function for efficient data compression, outperforming traditional wavelet methods, enhancing data storage needs, and improving diagnostic feature extraction.