1. A Data-Driven Comparative Analysis of Lithium-Ion Battery State of Health and Capacity Estimation.
- Author
-
Sheikh, Shehzar Shahzad, Shah, Fawad Ali, Athar, Syed Owais, and Khalid, Hassan Abdullah
- Subjects
LITHIUM-ion batteries ,CONVOLUTIONAL neural networks ,LONG-term memory ,COMPARATIVE studies ,MACHINE learning ,FEATURE extraction - Abstract
Researchers are focused toward the development of electric vehicles and hybrid electric vehicles for the preservation of the ecosystem. Energy storage, conversely, became essential with these changes in vehicular technology. This opens new research fronts and introduces complex problems that are to be investigated regarding the primary storage element. Battery modeling offers improved efficiency, safety, and reliability. Lithium-ion batteries are a popular source of energy in many applications, especially for electric vehicles because of their high performance and high energy density. However, there exist some inherent issues like complex electrochemical reactions that make accurate monitoring a challenging task. This article performs a comparative study of the existing battery state of health (SOH) monitoring and capacity estimation techniques using the NASA dataset for lithium-ion batteries. Charging cycle datasets for voltage, current, and temperature are used for feature identification and extraction. After the modeling of extracted features, the SOH and the capacity of four batteries are estimated using three data-driven techniques. Including convolutional neural network, feed-forward neural network, and long short-term memory (LSTM), and their results are compared. The comparative analysis highlights an outstanding performance and high accuracy of the LSTM-based machine learning technique because of the inherited long-term memory of the LSTM. The study, therefore, recommends the use of LSTM to researchers for battery health monitoring and capacity estimation with the highest possible accuracy. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF