A deep learning-based approach for accurate battery capacity prognostics

Fuente: Zenodo
Guardado en:
Detalles Bibliográficos
Autores principales: S., Ravikanth, Dr.G., Rajesh, Dr. T, Vamsee Kiran
Formato: Recurso digital
Lenguaje:inglés
Publicado: Zenodo 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866901655085121536
author S., Ravikanth
Dr.G., Rajesh
Dr. T, Vamsee Kiran
author_facet S., Ravikanth
Dr.G., Rajesh
Dr. T, Vamsee Kiran
contents <p><span>Prognostics and Health Management (PHM) is a crucial approach for battery systems, aiming to predict and manage system health to prevent failures and address potential issues. Accurate estimation ofbattery capacity is essential for proactive maintenance and replacement strategies, preventing unexpected failures, and optimising performance. Measurable data like voltage, current, and temperature profiles provide valuable insights into battery behaviour and performance. Accurate estimation of the state of health (SoH) is crucial for effective battery management and maintenance, enabling informed decisions on battery replacement, optimising battery lifespan, and maximising performance and longevity. This chapter uses various neural network models, such as Feed forward Neural Network (FNN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), to analyse battery capacity. Experiments were conducted on NASA-randomised datasets. The experimental results proved that the proposed models are better compared to the existing state-of-the-art methods in terms of accuracy, precision, and recall.</span></p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19198902
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle A deep learning-based approach for accurate battery capacity prognostics
S., Ravikanth
Dr.G., Rajesh
Dr. T, Vamsee Kiran
lithium-ion batteries
state of health
neural networks
capacity estimation
<p><span>Prognostics and Health Management (PHM) is a crucial approach for battery systems, aiming to predict and manage system health to prevent failures and address potential issues. Accurate estimation ofbattery capacity is essential for proactive maintenance and replacement strategies, preventing unexpected failures, and optimising performance. Measurable data like voltage, current, and temperature profiles provide valuable insights into battery behaviour and performance. Accurate estimation of the state of health (SoH) is crucial for effective battery management and maintenance, enabling informed decisions on battery replacement, optimising battery lifespan, and maximising performance and longevity. This chapter uses various neural network models, such as Feed forward Neural Network (FNN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), to analyse battery capacity. Experiments were conducted on NASA-randomised datasets. The experimental results proved that the proposed models are better compared to the existing state-of-the-art methods in terms of accuracy, precision, and recall.</span></p>
title A deep learning-based approach for accurate battery capacity prognostics
topic lithium-ion batteries
state of health
neural networks
capacity estimation
url https://doi.org/10.5281/zenodo.19198902