This study proposes a weighted ensemble deep learning framework for accurately predicting the State of Health (SOH) of lithium-ion batteries. Three distinct model architectures—CNN-LSTM, Transformer-LSTM, and CEEMDAN-BiGRU—are combined using a normalized inverse RMSE-based weighting scheme to enhance predictive performance. Unlike conventional approaches using fixed hyperparameter settings, this study employs Bayesian Optimization via Optuna to automatically tune key hyperparameters such as time steps (range: 10-35) and hidden units (range: 32-128). To ensure robustness and reproducibility, ten independent runs were conducted with different random seeds. Experimental evaluations were performed using the NASA Ames B0047 cell discharge dataset. The ensemble model achieved an average RMSE of 0.01381 with a standard deviation of ±0.00190, outperforming the best single model (CEEMDAN-BiGRU, average RMSE: 0.01487) in both accuracy and stability. Additionally, the ensemble's average inference time of 3.83 seconds demonstrates its practical feasibility for real-time Battery Management System (BMS) integration. The proposed framework effectively leverages complementary model characteristics and automated optimization strategies to provide accurate and stable SOH predictions for lithium-ion batteries.

1. 서 론
2. 관련 연구
3. 방법론
    3.1 데이터 및 전처리
    3.2 딥러닝 기반 예측 모델 구조
    3.3 하이퍼파라미터 최적화(Optuna의 BayesianOptimization 알고리즘)
    3.4 가중 앙상블
    3.5 데이터 분할 및 반복 실험 설계
4. 실험 및 결과
    4.1 실험 설계
    4.2 실험결과
5. 결론 및 향후 과제
References

• Daae Lee(Chungnam Technopark) | 이다애 (충남테크노파크)
• Guhyun Kwon(Chungnam Technopark) | 권구현 (충남테크노파크)
• Dongju Lee(Department of Industrial Engineering, Kongju National University) | 이동주 (공주대학교 산업공학과) Corresponding author
• Youngseok Kwon(Department of Industrial Engineering, Kongju National University) | 권영석 (공주대학교 산업공학과)