3d8d135818d1675848a-1a9a 20240320073338910 beie:beie director@blueeyesintelligence.org WEB-FORM International Journal of Recent Technology and Engineering (IJRTE) IJRTE 22773878 10.35940/ijrte.2277-3878 https://www.ijrte.org/ 03 30 2024 12 6 Department of Electrical Engineering Department, Politeknik Negeri Padang, Padang, Indonesia. Ismail https://orcid.org/0000-0003-0695-2494 Firdaus Department of Electrical Engineering Department, Negeri Padang, Padang, Padang, Indonesia. Rakiman Department of Mechanical Engineering, Politeknik Negeri Padang, Padang, Indonesia. Daddy Budiman Department of Mechanical Engineering, Politeknik Negeri Padang, Padang, Indonesia. Sardani Department of Electrical Engineering, Politeknik Negeri Padang, Padang, Indonesia. State of charge (SOC) estimation of lithium-ion batteries has been extensively studied and the estimation accuracy was mainly investigated through the development of various battery models and dynamic estimation algorithms. All battery models, however, contain inherent model bias due to the simplifications and assumptions, which cannot be effectively addressed through the development of various conventional computation and intelligent computation. Consequently, some existing methods performed battery SOC estimation using conventional and intelligent computation have not very accurate to predict the SOC battery characteristics. There some drawbacks in employment deep learning to estimate SOC battery, such as complicated algorithm or network, over fitting and so on. The proposed method, the Corny architecture has narrow layers design. This design has low cost computation and prevent over fitting. The result shows the accuracy of method is very high. The predicted and targeted values are almost merged in a single line. The RMSE and MAX error indexes are very low. That the accuracy of the model is acceptable. The electric vehicle battery can estimate to life longer and more reliable to perform mobility task. Finally, this method also show the accuracy of estimation SOC battery of electric vehicle can be solved by narrow learning layers. 03 30 2024 5-11 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true International Journal of Recent Technology and Engineering (IJRTE) Yes, This article receive partial support and was funded by politeknik negeri padang. The article is not be under Conflict of Interest. This is only a output of a research. All the authors are in one institution. This article does not require ethical approval and consent to participate. The data is obtain from mendeley dataset as cited in the article. The first author has major contribution in this article, the other four authors have equal participation at minor portion. 10.35940/ijrte.F7999.12060324 https://www.ijrte.org/portfolio-item/F799912060324/