Feature and LSTM-Based Capacity Prediction for Lithium-Ion Batteries: Application of Linear Regression and LSTM Models, with Future Expansion to Fuel Cell Datasets and Optimization

<p class="MsoNormal"><span lang="EN-US" style="mso-bidi-font-size:10.0pt;font-family:&quot;Arial&quot;,sans-serif">Lithium-ion battery capacity forecasting iscritical to optimizing energy storage devices, and equivalent forecasts forfuel cells are needed to attain power generation efficiency and extended systemlives. The current research used discharge data with lithium-ion batterycapacity values to create four single time-series data sets, of which 10features per series were created, resulting in 40 feature matrices. Both linearregression and Long Short-Term Memory (LSTM) models were used to predictbattery capacity. The linear regression model worked with an RMSE of 0.0058, andthe LSTM-based model was compared based on RMSE and loss function metrics. Theresults indicate the possibility of applying these methods to predict capacityaccurately. The proposed approach sets a foundation for subsequent optimizationand adjustment toward fuel cell data for more stable prediction and bettercontrol over the energy system in future work.</span><b><span lang="EN-US" style="font-family:&quot;Arial&quot;,sans-serif"><o:p></o:p></span></b>