2026-10-14T08:18:28Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34018844 2026-09-29T01:04:31Z category_15 category_734 category_106 category_122 portal_63 item_type_6 month_year_09_2026

Battery Electrode Design Process Using Deep Neural Network Hyeonghun Park (25133624) Joosoon Lee (25133627) Hyungi Song (25133630) Kyoobin Lee (25133633) Hyeong-Jin Kim (2459959) Neuroscience Biological Sciences not elsewhere classified Science Policy Mental Health world experimental data power density requirements inverse design framework including loading level explored region satisfied explored parameters matched electrode design parameters cells fabricated within accelerate lib design error optimization costly deep learning model 2 </ sup target rate capability rate capability deep learning r </ >< sup average error trained entirely target performance study presents results demonstrate practical feasibility merely 4 ion batteries intricate trade ev industry electric vehicles diverse energy demands lithium collectively representing battlenet achieved battlenet ), 9 %, 5 %. The transition to electric vehicles (EVs) demands lithium-ion batteries (LIBs) customized for diverse energy and power density requirements, yet the intricate trade-offs among electrode design parameters make conventional trial-and-error optimization costly and time-consuming. This study presents the battery electrode exploration network (BattleNet), a deep learning model that predicts the specific capacity across multiple C-rates, collectively representing the rate capability, from electrode design parameters, including loading level, thickness, and porosity. Trained entirely on real-world experimental data, BattleNet achieved an <i>R</i>² of 0.889, outperforming conventional machine learning baselines. Based on these predictions, an inverse design framework was proposed to explore design parameters satisfying a target rate capability. The explored parameters matched the target with an average error of 7.9%, and cells fabricated within the explored region satisfied the target performance with an average error of merely 4.5%. These results demonstrate the practical feasibility of deep learning as a tool to accelerate LIB design and development for the EV industry. 2026-09-28T00:00:00Z Text Journal contribution 10.1021/acsomega.6c05440.s001 https://figshare.com/articles/journal_contribution/Battery_Electrode_Design_Process_Using_Deep_Neural_Network/34018844 CC BY-NC 4.0