Neural Network Driven by Electrochemical Performance Data for Predicting the Discharge Termination Time of Seawater Electrolyte-Based Metal-Air Batteries

Authors

• Peng-Peng Shen, State Key Laboratory of Tropic Ocean Engineering Materials and Materials Evaluation, School of Information and Communication Engineering, School of Electronic Science and Technology, Hainan University, Haikou 570228, China.
• Yi-Chi Pan, State Key Laboratory of Tropic Ocean Engineering Materials and Materials Evaluation, School of Information and Communication Engineering, School of Electronic Science and Technology, Hainan University, Haikou 570228, China.
• Yu-Rong Liu, State Key Laboratory of Tropic Ocean Engineering Materials and Materials Evaluation, School of Information and Communication Engineering, School of Electronic Science and Technology, Hainan University, Haikou 570228, China.
• Lu-Dan Zhang, State Key Laboratory of Tropic Ocean Engineering Materials and Materials Evaluation, School of Information and Communication Engineering, School of Electronic Science and Technology, Hainan University, Haikou 570228, China.
• Ning Niu, State Key Laboratory of Tropic Ocean Engineering Materials and Materials Evaluation, School of Information and Communication Engineering, School of Electronic Science and Technology, Hainan University, Haikou 570228, China.
• Guan-Jun Wang, State Key Laboratory of Tropic Ocean Engineering Materials and Materials Evaluation, School of Information and Communication Engineering, School of Electronic Science and Technology, Hainan University, Haikou 570228, China.Follow
• De-Kun Yang, State Key Laboratory of Tropic Ocean Engineering Materials and Materials Evaluation, School of Information and Communication Engineering, School of Electronic Science and Technology, Hainan University, Haikou 570228, China.Follow
• Xin-Long Tian, State Key Laboratory of Tropic Ocean Engineering Materials and Materials Evaluation, School of Information and Communication Engineering, School of Electronic Science and Technology, Hainan University, Haikou 570228, China.Follow
• Peng Rao, State Key Laboratory of Tropic Ocean Engineering Materials and Materials Evaluation, School of Information and Communication Engineering, School of Electronic Science and Technology, Hainan University, Haikou 570228, China.Follow

Document Type

Article

Corresponding Author(s)

Guan-Jun Wang([email protected]);
Dekun Yang([email protected]);
Xin-Long Tian([email protected]);
Peng Rao([email protected])

Abstract

Seawater electrolyte-based metal-air batteries exhibit great promise for marine energy supply systems. However, conventional statistical analysis methods, though applicable to seawater metal-air battery lifetime prediction, have inherent limitations of insufficient prediction accuracy and large error. Herein, a deep time-series regression framework based on InceptionTime and incorporating prior-biased attention pooling is proposed to construct a nonlinear mapping between electrochemical performance sequences and the discharge termination time of catalysts. Specifically, chronoamperometry profiles are employed to extract long-term stability features, while prior knowledge derived from linear sweep voltammetry is introduced to strengthen the attention weighting over critical potential regions. Under a nested leave-one-catalyst-out cross-validation framework with the one-standard-error rule for epoch selection, the model demonstrates high consistency across various aggregation strategies on a small-sample test set containing different air cathode catalysts, yielding a coefficient of determination (R2) of over 0.90. These findings suggest that integrating multiscale temporal features with electrochemical prior knowledge through an attention-driven regression framework can improve the prediction accuracy and reduce the prediction error of discharge termination time in the current dataset, thereby providing a preliminary data-driven approach for catalyst evaluation in seawater metal-air batteries.

Graphical Abstract

Keywords

Seawater metal-air batteries, Electrochemical performance, Catalyst failure time prediction, Time series regression

DOI

10.61558/2993-074X.3616

Online Date

5-14-2026

Recommended Citation

Peng-Peng Shen, Yi-Chi Pan, Yu-Rong Liu, Lu-Dan Zhang, Ning Niu, Guan-Jun Wang, De-Kun Yang, Xin-Long Tian, Peng Rao. Neural Network Driven by Electrochemical Performance Data for Predicting the Discharge Termination Time of Seawater Electrolyte-Based Metal-Air Batteries[J]. Journal of Electrochemistry, doi: 10.61558/2993-074X.3616.