The instability of lithium-ion batteries may result in system operation failure and cause safety accidents, thus predicting the remaining useful life (RUL) accurately is helpful for reducing the risk of battery failure and extending its useful life. In this paper, a hybrid model based on TCN-GRU-DNN and dual attention mechanism is proposed for enhancing the RUL prediction accuracy of lithium-ion batteries. Firstly, the Temporal Convolutional Network (TCN) with a feature attention mechanism is applied to form an encoder module to capture the battery capacity regeneration phenomenon, and then a Gated Recurrent Unit (GRU) with a temporal attention mechanism is denoted as a decoder module for better characterizing the decay trend of the capacity series. Finally, the final prediction results are output through a Deep Neural Network (DNN). We conducted experiments on two data sets NASA and CALCE. The prediction errors are presented in subsequent experiments under different evaluation standards such as absolute error (AE), root mean square error (RMSE), mean absolute error (MAE), and R-squared error (R²). The experimental results demonstrate that the proposed model can achieve a more accurate prediction for RUL on lithium-ion batteries, with RMSE does not exceed 2.407% in the NASA dataset and does not exceed 0.897% in the CALCE lithium-ion battery dataset respectively.

Determination of the electrochemical active thickness (EAT) is of paramount importance for optimizing the solid oxide fuel cell (SOFC) electrode. However, very different EAT values are reported in the previous literatures. This paper aims to systematically study the EAT of SOFC anode numerically. An SOFC model coupling electrochemical reactions with transport of gas, electron and ion is developed. The microstructure features of the electrode are modeled based on the percolation theory and coordinate number theory. Parametric analysis is performed to examine the effects of various operating conditions and microstructures on EAT. Results indicate that EAT increases with decreasing exchange current density (or decreasing TPB length) and increasing effective ionic conductivity. In addition to the numerical simulations, theoretical analysis is conducted including various losses in the electrode, which clearly shows that the EAT highly depends on the ratio of concentration related activation loss R-act,R-con to ohmic loss R-ohmic. The theoretical analysis explains very well the different EATs reported in the literature and is different from the common understanding that the EAT is controlled mainly by the ionic conductivity of electrode.Department of Building and Real Estat