Search

Future capacity prediction of lithium-ion batteries is a highly researched topic in the field of battery management systems, owing to the gradual degradation of battery capacity over time due to various factors such as chemical changes within the battery, usage patterns, and operating conditions. The accurate prediction of battery capacity can aid in optimizing its usage, extending its lifespan, and mitigating the risk of unforeseen failures. In this paper, we proposed a novel fine-tuning model based on a deep learning model with a transfer learning approach comprising of two key components: offline training and online prediction. Model weights and prediction parameters were transferred from offline training using source data to the online prediction stage. The transferred Bi-directional Long Short-Term Memory with an Attention Mechanism model weights and prediction parameters were utilized to fine-tune the model by partial target data in the online prediction phase. Three battery batches with different charging policy were used to evaluate the proposed approach’s robustness, reliability, usability, and accuracy for the three charging policy batteries’ real-world data. The experiment results show that the proposed method’s efficacy improved, with an increase in the cycle number of the starting point, exhibiting a linear relationship with the starting point. The proposed method yields relative error values of 8.70%, 6.38%, 9.52%, 7.58%, 1.94%, and 2.29%, respectively, for the six target batteries in online prediction. Thus, the proposed method is effective in predicting the future capacity of lithium-ion batteries and holds potential for use in predictive maintenance applications.

Lithium-ion (Li-ion) batteries are considered to be one of the ideal energy sources for automotive and electronic products due to their size, high levels of charge, higher energy density, and low maintenance. When Li-ion batteries are used in harsh environments or subjected to poor charging habits, etc., their degradation will be accelerated. Thus, online state of health (SOH) estimation becomes a hot research topic. In this study, normalized capacity is considered as SOH for the estimation and calculation of remaining useful lifetime (RUL). A multi-step look-ahead forecast-based deep learning model is proposed to obtain SOH estimates. A total of six batteries, including three as source datasets and three as target datasets, are used to validate the deep learning model with a transfer learning approach. Transferability measures are used to identify source and target domains by accounting for cell-to-cell differences in datasets. With regard to the SOH estimation, the root mean square errors (RMSEs) of the three target batteries are 0.0070, 0.0085, and 0.0082, respectively. Concerning RUL prediction performance, the relative errors of the three target batteries are obtained as 2.82%, 1.70%, and 0.98%, respectively. In addition, all 95% prediction intervals of RUL on the three target batteries include the end-of-life (EOL) value (=0.8). These results indicate that our method can be applied to battery SOH estimation and RUL prediction.

Proton exchange membrane fuel cell (PEMFC) is a clean and efficient alternative technology for transport applications. The degradation analysis of the PEFMC stack plays a vital role in electric vehicles. We propose a hybrid method based on a deep neural network model, which uses the Monte Carlo dropout approach called MC-DNN and a sparse autoencoder model to analyze the power degradation trend of the PEMFC stack. The sparse autoencoder can map high-dimensional data space to low-dimensional latent space and significantly reduce noise data. Under static and dynamic operating conditions, using two experimental PEMFC stack datasets the predictive performance of our proposed model is compared with some published models. The results show that the MC-DNN model is better than other models. Regarding the remaining useful life (RUL) prediction, the proposed model can obtain more accurate results under different training lengths, and the relative error between 0.19% and 1.82%. In addition, the prediction interval of the predicted RUL is derived by using the MC dropout approach.