Sources and links on page 230 (1)
Links embedded in the original report PDF, including citations and other references. These destinations have not been independently reviewed. Links open in a new tab.
Text on page 230
Cloud-Based Battery Prognostics And Health Management
Machine Learning
Cloud-Based Battery Prognostics And Health Management
Developing a cloud computing pipeline with ML for accurate in-situ battery life prediction In-situ battery life prediction and classification are important to lithium-ion battery prognostics and health management (PHM). This research proposes a cloud-based PHM pipeline with a novel physical features-driven moving-window ML model, which can be used to predict the battery remaining useful life and knee-point. The proposed ML model is validated based on experimental data from a batch of 124 LFP/graphite cells from A123. The results show that the method predicts remaining useful life and knee-point accurately (with extremely small prediction error.
Machine learning is used to capture the relationship between physical features and battery life, demonstrating high accuracy in remaining useful life and knee-point prediction, with low errors of 55 cycles and 3.55% respectively.
Academia | P. 230 Source: Zhang, Yongzhi, and Mingyuan Zhao
Extracted from the PDF; charts and images may read imperfectly.
Page 230 · 3/5