Session: AVT-05-01 Advances in Vehicle Electrification and Powertrain Design

Paper Number: 89512

89512 - Artificial Intelligence Based State of Health Estimation With Short-Term Current Profile in Lead-Acid Batteries for Heavy-Duty Vehicles 

The State of Health (SOH) estimation for automotive batteries is currently assessed with different techniques. In this context, an accurate SOH estimation aims to improve cost reduction because of better maintenance planning and better management of the battery pack during recharging phases, while providing a consequent enhancement in the performance of State of Charge (SOC) estimation methods. This paper presents the design and validation of a SOH method with a short-term current profile using Artificial Intelligence (AI) in lead-acid batteries, which are commonly used in heavy-duty vehicles for cranking and cabin systems. The paper validates the considered approach with experimental data, that are representative of actual vehicle operations. In detail, the paper describes the retained hardware and software architectures and the design procedure related to the proposed SOH estimation technique based on AI. The retained lead-acid battery 12 V 225 Ah battery used in actual heavy-duty vehicles. The proposed AI-based algorithm relies on an Artificial Neural Network (ANN) used for SOH classification, which is trained with a sufficient amount of collected data. Specifically, the proposed SOH classifier can process features extracted from buffers of input data that are recorded onboard. When considering the validation dataset only, the resulting SOH estimation algorithm can classify the battery SOH with an overall accuracy equal to 96.7%.

Presenting Author: Sara Luciani Politecnico di Torino

Presenting Author Biography: NA

Authors:

Sara Luciani Politecnico di Torino
Stefano Feraco Politecnico di Torino
Angelo Bonfitto Politecnico di Torino
Nicola Amati Politecnico di Torino
Andrea Tonoli Politecnico di Torino
Maurizio Quaggiotto IVECO Group