A review on data-driven SOC estimation with Li-Ion batteries: Implementation methods &amp; future aspirations

R., S.; Badachi, Chandrashekhar; Green, Robert C.

doi:10.1016/j.est.2023.108420

Cited by 18 publications

(1 citation statement)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TinyML has been identified as one of the most promising frontiers in data-driven SoC estimation, with embedded edge sensor devices used to create smart battery packs that can conduct a real-life evaluation of the performance and states of the battery [27]. The challenge of designing and optimizing an ML model on low-power Internet of Things (IoT) devices comes with a lot of benefits, including energy efficiency, low cost, low latency, and the ability to perform local data processing, avoiding unnecessary data transfers [28].…”

Section: Tinyml For Sox Etimationmentioning

confidence: 99%

A Case Study of a Tiny Machine Learning Application for Battery State-of-Charge Estimation

Giazitzis,

Sakwa,

Leva

et al. 2024

Electronics

View full text Add to dashboard Cite

Growing battery use in energy storage and automotive industries demands advanced Battery Management Systems (BMSs) to estimate key parameters like the State of Charge (SoC) which are not directly measurable using standard sensors. Consequently, various model-based and data-driven approaches have been developed for their estimation. Among these, the latter are often favored due to their high accuracy, low energy consumption, and ease of implementation on the cloud or Internet of Things (IoT) devices. This research focuses on creating small, efficient data-driven SoC estimation models for integration into IoT devices, specifically the Infineon Cypress CY8CPROTO-062S3-4343W. The development process involved training a compact Convolutional Neural Network (CNN) and an Artificial Neural Network (ANN) offline using a comprehensive dataset obtained from five different batteries. Before deployment on the target device, model quantization was performed using Infineon’s ModusToolBox Machine Learning (MTB-ML) configurator 2.0 software. The tests show satisfactory results for both chosen models with a good accuracy achieved, especially in the early stages of the battery lifecycle. In terms of the computational burden, the ANN has a clear advantage over the more complex CNN model.

show abstract

Section: Tinyml For Sox Etimationmentioning

confidence: 99%