LSTM-Powered Failure Forecasting: Boosting Battery Production Efficiency with Machine Learning

• Shinichi Ishii UFAM
• Ana Cláudia de Araújo Moxotó UFAM
• Edjard Mota UFAM

DOI: https://doi.org/10.5753/eniac.2025.11873

Resumo

The growing adoption of Artificial Intelligence and machine learning in the industry aims to optimize processes and support decisions. In the electronics sector, electrical tests on components such as battery boards generate vast volumes of data that are often underutilized, while recurrent failures increase costs and affect productivity. This work proposes a predictive model based on recurrent neural networks to predict failures in battery boards from the analysis of historical test data. In our methodology, we first removed outliers and missing values. Then, we developed two recurrent neural network models, LSTM and GRU, to evaluate which would perform better as a prediction model. The results demonstrated that the LSTM 1 and GRU 1 models effectively generated predictions. Failure predictions, such as the 11 identified in the subsequent five days for the Operating Current variable, provide valuable strategic insights. This approach enables managers to make more assertive decisions and implement preventive actions, such as the early replacement of consumables, in order to reduce input costs and minimize unplanned downtime, optimizing efficiency in manufacturing systems.

Palavras-chave: Machine Learning, Prediction, LSTM, GRU, Batteries

Referências

Chemali, E., Kollmeyer, P. J., Preindl, M., Ahmed, R., and Emadi, A. (2018). Long shortterm memory networks for accurate state-of-charge estimation of li-ion batteries. IEEE Transactions on Industrial Electronics, 65:6730–6739.

Chicco, D., Warrens, M. J., and Jurman, G. (2021). The coefficient of determination r-squared is more informative than smape, mae, mape, mse and rmse in regression analysis evaluation. PeerJ Computer Science, 7:e623.

Fischer, T. and Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270:654–669.

Gil, A. C. (2009). Estudo de caso. Atlas, 1ª edition.

Gunckel, P. V., Lobos, G., Rodríguez, F. K., Bustos, R. M., and Godoy, D. (2025). Methodology proposal for the development of failure prediction models applied to conveyor belts of mining material using machine learning. Reliability Engineering & System Safety, 256:110709.

Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8):1735–1780.

Hyndman, R. J. and Koehler, A. B. (2006). Another look at measures of forecast accuracy. International Journal of Forecasting, 22:679–688.

Joglekar, Y. N. and Wolf, S. J. (2009). The elusive memristor: properties of basic electrical circuits. European Journal of Physics, 30:661–675.

Jordan, M. I. and Mitchell, T. M. (2015). Machine learning: Trends, perspectives, and prospects. Science, 349:255–260.

Kashpruk, N., Piskor-Ignatowicz, C., and Baranowski, J. (2023). Time series prediction in industry 4.0: A comprehensive review and prospects for future advancements. Applied Sciences, 13(22).

Liu, H., Li, C., Hu, X., Li, J., Zhang, K., Xie, Y., Wu, R., and Song, Z. (2025). Multimodal framework for battery state of health evaluation using open-source electric vehicle data. Nature Communications, 16(1):1137.

Liu, K., Shang, Y., Ouyang, Q., and Widanage, W. D. (2021). A data-driven approach with uncertainty quantification for predicting future capacities and remaining useful life of lithium-ion battery. IEEE Transactions on Industrial Electronics, 68:3170–3180.

Neupane, D., Bouadjenek, M. R., Dazeley, R., and Aryal, S. (2025). Data-driven machinery fault diagnosis: A comprehensive review. Neurocomputing, 627:129588.

Patrizi, G., Martiri, L., Pievatolo, A., Magrini, A., Meccariello, G., Cristaldi, L., and Nikiforova, N. D. (2024). A review of degradation models and remaining useful life prediction for testing design and predictive maintenance of lithium-ion batteries. Sensors, 24(11):3382.

Sharma, P. and Bora, B. J. (2023). A review of modern machine learning techniques in the prediction of remaining useful life of lithium-ion batteries. Batteries, 9(1).

Siami-Namini, S., Tavakoli, N., and Namin, A. S. (2018). A comparison of arima and lstm in forecasting time series. In 2018 17th IEEE international conference on machine learning and applications (ICMLA), pages 1394–1401. Ieee.

Sisode, M. and Devare, M. (2023). A review on machine learning techniques for predictive maintenance in industry 4.0. In Proceedings of the International Conference on Applications of Machine Intelligence and Data Analytics (ICAMIDA 2022), pages 774–783. Atlantis Press.

Thelen, A., Huan, X., Paulson, N., Onori, S., Hu, Z., and Hu, C. (2024). Probabilistic machine learning for battery health diagnostics and prognostics—review and perspectives. npj Materials Sustainability, 2(1):14.

Tong Poh, W. Q., Xu, Y., and Poh Tan, R. T. (2022). A review of machine learning applications for li-ion battery state estimation in electric vehicles. In 2022 IEEE PES Innovative Smart Grid Technologies - Asia (ISGT Asia), pages 265–269.

Vamathevan, J., Clark, D., Czodrowski, P., Dunham, I., Ferran, E., Lee, G., Li, B., Madabhushi, A., Shah, P., Spitzer, M., and Zhao, S. (2019). Applications of machine learning in drug discovery and development. Nature Reviews Drug Discovery, 18:463–477.

Wen, Q., Gao, J., Song, X., Sun, L., Xu, H., and Zhu, S. (2019). Robuststl: A robust seasonal-trend decomposition algorithm for long time series. Proceedings of the AAAI Conference on Artificial Intelligence, 33:5409–5416.

Wuest, T., Weimer, D., Irgens, C., and Thoben, K.-D. (2016). Machine learning in manufacturing: advantages, challenges, and applications. Production & Manufacturing Research, 4:23–45.

Zhang, Y., Xiong, R., He, H., and Pecht, M. G. (2018). Long short-term memory recurrent neural network for remaining useful life prediction of lithium-ion batteries. IEEE Transactions on Vehicular Technology, 67:5695–5705.

Zhao, J., Li, D., Li, Y., Shi, D., Nan, J., and Burke, A. F. (2025). Battery state of health estimation under fast charging via deep transfer learning. iScience, 28(5).