On-Road Experimental Campaign for Machine Learning Based State of Health Estimation of High-Voltage Batteries in Electric Vehicles

Abstract

The present study investigates the use of machine learning algorithms to estimate the state of health (SOH) of high-voltage batteries in electric vehicles. The analysis is based on open-circuit voltage (OCV) measurements from 12 vehicles with different mileage conditions and focuses on establishing a correlation between the OCV values, the energy stored in the battery, and the battery SOH. The experimental campaign was conducted at the Hyundai Motor Europe Technical Center GmbH (Germany), and the data collection process took advantage of the ETAS Integrated Calibration and Application Tool (INCA) and the ETAS Measure Data Analyzer (MDA) software. Six machine learning algorithms are evaluated and compared, namely linear regression, k-nearest neighbors, support vector machine, random forest, classification and regression tree, and neural network. Among the evaluated algorithms, random forest (RF) exhibits the best performance in predicting the state of health of high-voltage batteries, both for the OCV and the capacity (C) estimation. Specifically, if compared to the worst algorithm (i.e., linear regression), RF achieves a remarkable improvement with a reduction of 96% and 97% in the mean absolute error for the OCV and the C estimation, respectively. Furthermore, the comparison highlighted the main differences in the performance, complexity, interpretability, and specific features of the six algorithms. The findings of the present study will contribute to the development of efficient maintenance strategies, thus reducing the risk of unexpected battery failures.

Optimizing EV Battery Management: Advanced Hybrid Reinforcement Learning Models for Efficient Charging and Discharging

“…Effective energy management enables the seamless integration of these batteries into larger energy systems, promoting grid stability and facilitating smoother energy transitions [6]. Understanding the fundamental working principles and components of lithium-ion batteries, which operate based on electrochemical principles involving the movement of ions between two electrodes through an electrolyte, is essential [7].…”

Energy Management in Hybrid Electric Vehicles: A Q-Learning Solution for Enhanced Drivability and Energy Efficiency

“…In this context, a bridge solution may be represented by hybrid electric vehicles (HEVs). According to several statistical analyses available online, the hybrid market is expected to grow by 20% over the next five years, with the plug-in segment leading the way [1,2]. From a technical point of view, hybrid electric vehicles combine the main advantages of conventional and fully electric vehicles; however, owing to their complex nature, they require sophisticated control logic to obtain a proper energy split among the on-board energy sources, making them widely investigated in the literature.…”

“…FC = Fuel consumption; f ICE = Frequency of ICE activations; FC corr = Corrected fuel consumption 2. Correction of fuel consumption to account for SOC variation 3.…”