Towards the Development of Machine Learning Models for Deep Cycle Battery Performance Analysis: Research Gap Identification via Bibliometric Analysis and Global Evidence Mapping

Authors: Obayuwana, A. And Okoye, J.U.

DOI Info: http://doi.org/10.5281/zenodo.8094134

ABSTRACT

The use of machine learning has recently increased in the field of energy storage. This is due to the level of accuracy and convenience in estimating battery states like the state of health (SOH), state of charge (SOC), and remaining useful life (RUL) which is used to estimate the performance of the battery. A lot of researchers have used machine models to estimate these battery states. These models each differ in approach, outcome, and effectiveness. This study was undertaken to identify research gaps in topics related to machine learning models for battery performance analysis. These related works were identified using bibliometric analysis coupled with a systematic literature review of the study search index through the Scopus database-indexed publications. The results from this study show 286 articles selected from 3,086 documents identified via a visualization of the network map rendered using VOSviewer. Sensitivity analysis, cycle life, and lead acid batteries were revealed as the particular research gaps. The study also presented results of mapping different methods used to identify, prioritize, and visualize research gaps. The study output would prove a useful resource for quick insight into the techniques and methodologies in this field.

Download Full Text