Cross Trajectory Gaussian Process Regression Model for Battery Health Prediction

Accurate battery capacity prediction is important to ensure reliable operation and reduce the cost. However, complex nature of degradation presence regeneration phenomenon render task very challenging. To address this problem, paper proposes a novel efficient algorithm predict trajectory in multi-cell setting. The proposed method new variant Gaussian process regression (GPR) model, it utilizes similar trajectories historical data enhance desired trajectory. More importantly, adds no extra computation cost standard GPR. demonstrate effectiveness method, validation tests on two different datasets are implemented case studies. results carefully benchmarked with cutting-edge GPR approaches for prediction.