.png){kind=icon}
.png){kind=icon}
Return
Large language models for battery prognostics
.png){kind=icon}
OA
AI
DOI：10.1016/j.jechem.2025.11.021.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Predicting battery health with accuracy and interpretability has become a grand challenge at the intersection of electrochemistry, artificial intelligence, and sustainable energy. Conventional data-driven and physics-based methods remain constrained by nonlinear, coupled, and heterogeneous battery dynamics that limit generalization across chemistries, duty cycles, and environments. Recent breakthroughs in large language models (LLMs) and foundation-model artificial intelligence introduce a paradigm shift—enabling machines to learn from multimodal signals, encode physical laws, and reason adaptively across scales. This review unifies these advances into ten foundational methodologies that delineate the emerging landscape of intelligent battery prognostics: transfer learning, knowledge augmentation, physics-informed and explainable intelligence, ensemble fusion, causal reasoning, continual adaptation, multi-agent coordination, digital-twin coupling, and the pursuit of artificial general intelligence. Together, these dimensions redefine batteries from passive electrochemical devices into cognitive energy systems—self-optimizing, trustworthy, and responsive to uncertainty. Framed within the broader evolution toward Industry 5.0, we chart a roadmap for autonomous battery management that fuses physics, data, and reasoning, establishing artificial intelligence as a scientific and technological cornerstone for the next generation of resilient, adaptive, and sustainable electrification.
Keywords:
Battery management system
Artificial intelligence
Deep learning
Large language models
Multi-agent
Artificial general intelligence
Industry 5.0
AGI
Artificial general intelligence
AI
Artificial intelligence
BMS
Battery management system
DV
Differential voltage
DVA
Differential-voltage analysis
EIP
Electrochemically inactive phase
EIS
Electrochemical impedance spectroscopy
ESS
Energy storage systems
EV
Electric vehicle
FMEA
Failure mode and effects analysis
GAN
Generative adversarial network
IC
Incremental capacity
IoT
Internet of Things
LAM
Loss of active material
LFP
Lithium iron phosphate
LLI
Loss of lithium inventory
LLMs
Large language models
LoRA
Low-rank adaptation
LSTM
Long short-term memory network
MAPE
Mean absolute percentage error
OTA
Over the air
PDE
Partial differential equation
PINN
Physics-informed neural network
PNNL
Pacific Northwest National Laboratory
RAG
Retrieval-augmented generation
RUL
Remaining useful life
SCM
Structural causal model
SEI
Solid-electrolyte interphase
SLMs
Small language models
SOC
State of charge
SOH
State of health
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
14.9
Papers:
6.3K
Citations:
4.5W
View more organizations