Research map / Probabilistic and scientific modeling / Differential equations and PDEs
MINN: Learning the Dynamics of Differential-Algebraic Equations and Application to Battery Modeling
Yicun Huang, Changfu Zou, Yang Li, Torsten Wik
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| learn algebraic variables with a physics-integrated recurrent unit (MINN) instead of supervised DD-ROM on internal states | battery DAE model · Dynamic driving profile | plating potential RMSE (mV): 9.88 -> 6.28 | Improved |
| use MINN instead of DD-ROM | battery DAE model · Dynamic driving profile | SOC RMSE (%): 0.635 -> 0.059 | Improved |
| use MINN instead of DD-ROM | battery DAE model · Dynamic driving profile | terminal voltage RMSE (mV): 9.87 -> 11.6 | Hurt |
| use MINN instead of DD-ROM | battery DAE model · 800 s driving test | average solution speedup vs P2D: 91X -> 182X | Improved |
| use MINN's low-order model instead of DD-ROM | battery DAE model · Model complexity | model order: 130 -> 82 | Improved |
| use MINN instead of DD-ROM | battery DAE model · Model complexity | maximum Jacobian condition number: 6.7 x 10^9 -> 3.0 x 10^8 | Improved |
| replace P2D DAE with MINN ODE | P2D battery model · 800 s driving test | average solution speedup: 1X -> 182X | Improved |
| use MINN instead of NODE, DNN and PINN under 1C charge extrapolation | battery electrolyte concentration prediction · 1C charge, test 300-1200 s | electrolyte concentration MAPE | Improved |
Closest papers by meaning
- NOCE-Net: Representation Learning for Battery Operational Context via Nested Sequence Modelling (NeurIPS 2026 · similarity 0.85)
- BatteryML: An Open-source Platform for Machine Learning on Battery Degradation (ICLR 2024 · similarity 0.84)
- Semi-supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach (AAAI 2024 · similarity 0.84)
- Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification (ICML 2024 · similarity 0.83)
- Stable Port-Hamiltonian Neural Networks (NeurIPS 2025 · similarity 0.83)
- ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence (NeurIPS 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
