Huhe Dai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Huhe Dai has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Caili Gong
College of Electronic Information Engineering, Inner Mongolia University, China
1 shared publication - Chuanfeng Li
School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China
1 shared publication - Daoerji Fan
School of Electronic Information Engineering, Inner Mongolia University, Hohhot 010021, China
1 shared publication - Xin Zhao
School of Electronic Information Engineering, Inner Mongolia University, Hohhot, China
1 shared publication Xingyu He
1 shared publicationYang Yu
1 shared publication
Latest Publications
- Open Access
- 21 October 2026
- Published by Elsevier in SSRN Electronic Journal
Cross-cell SOH prediction of lithium-ion batteries based on SPMe parameter identification
Cell-to-cell variations in degradation trajectories limit the cross-cell generalization of state of health (SOH) prediction models trained on one lithium-ion cell. Training with labeled data from multiple cells can improve generalization, but SOH labels can only be obtained through full-capacity tests that interrupt operation, making such data difficult to acquire. To solve this problem, this paper proposes a cross-cell SOH prediction framework based on the single particle model with electrolyte dynamics (SPMe). Automatic matching of baseline parameter sets and two-stage particle swarm optimization identify electrochemical parameters from the discharge voltage and current of each cycle, producing parameter sequences for each cell. For each dataset group, only one cell with SOH labels is used for feature selection and model training. Electrochemical features are selected by considering their correlations with SOH in the training cell, parameter redundancy, and physical meaning. A long short-term memory network learns the relationship between the selected feature sequences and SOH to predict future SOH values. The trained model is directly applied to target cells without adaptation. Target-cell SOH labels are used only for evaluation. The framework is validated on five dataset groups covering four cathode materials. With equal weighting across groups, the root mean square error and mean absolute error for 10-step-ahead prediction are 0.0269 and 0.0212, respectively. These values are 12.52% and 15.06% lower than those obtained using voltage statistical features. The results show that electrochemical parameters identified using the SPMe provide useful degradation information for cross-cell SOH prediction without target-cell SOH labels during model development.
- 21 October 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessCross-cell SOH prediction of lithium-ion batteries based on SPMe parameter identification
Cell-to-cell variations in degradation trajectories limit the cross-cell generalization of state of health (SOH) prediction models trained on one lithium-ion cell. Training with labeled data from multiple cells can improve generalization, but SOH labels can only be obtained through full-capacity tests that interrupt operation, making such data difficult to acquire. To solve this problem, this paper proposes a cross-cell SOH prediction framework based on the single particle model with electrolyte dynamics (SPMe). Automatic matching of baseline parameter sets and two-stage particle swarm optimization identify electrochemical parameters from the discharge voltage and current of each cycle, producing parameter sequences for each cell. For each dataset group, only one cell with SOH labels is used for feature selection and model training. Electrochemical features are selected by considering their correlations with SOH in the training cell, parameter redundancy, and physical meaning. A long short-term memory network learns the relationship between the selected feature sequences and SOH to predict future SOH values. The trained model is directly applied to target cells without adaptation. Target-cell SOH labels are used only for evaluation. The framework is validated on five dataset groups covering four cathode materials. With equal weighting across groups, the root mean square error and mean absolute error for 10-step-ahead prediction are 0.0269 and 0.0212, respectively. These values are 12.52% and 15.06% lower than those obtained using voltage statistical features. The results show that electrochemical parameters identified using the SPMe provide useful degradation information for cross-cell SOH prediction without target-cell SOH labels during model development.
- Open Access
- 22 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 116-120
Explore a novel multi-dimensional collaborative cultivating mechanism for engineering graduate students under the background of “AI+”
Aiming at the cultivation concept of high-level innovative talents in the new era, according to the training objectives and positioning of new engineering students, the innovation ability and practical ability still need to be further strengthened and improved. In order to make up for the practical defects that the conventional graduate training model does not provide students with opportunities and platforms to organically integrate and apply specific engineering problems and theoretical knowledge, this paper will explore and study a new teaching and training mode based on the background of "AI+(Artificial Intelligence +)", which focuses on improving and strengthening the innovation and practical ability of new engineering students through the mechanism of project-led and multi-dimensional collaboration. The authors put forward a set of teaching mode to stimulate students to dig and solve practical engineering problems. By adopting the "AI+ industry-specific application" strategy in teaching, the model guides students to make full use of AI models and algorithms, and closely integrate course content with specific problems in specific industries. By applying this teaching mode to students of grade 2019, good results have been achieved.
- 22 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 116-120
Open AccessExplore a novel multi-dimensional collaborative cultivating mechanism for engineering graduate students under the background of “AI+”
Aiming at the cultivation concept of high-level innovative talents in the new era, according to the training objectives and positioning of new engineering students, the innovation ability and practical ability still need to be further strengthened and improved. In order to make up for the practical defects that the conventional graduate training model does not provide students with opportunities and platforms to organically integrate and apply specific engineering problems and theoretical knowledge, this paper will explore and study a new teaching and training mode based on the background of "AI+(Artificial Intelligence +)", which focuses on improving and strengthening the innovation and practical ability of new engineering students through the mechanism of project-led and multi-dimensional collaboration. The authors put forward a set of teaching mode to stimulate students to dig and solve practical engineering problems. By adopting the "AI+ industry-specific application" strategy in teaching, the model guides students to make full use of AI models and algorithms, and closely integrate course content with specific problems in specific industries. By applying this teaching mode to students of grade 2019, good results have been achieved.