Adapting Amidst Degradation: Cross Domain Li-ion Battery Health Estimation via Physics-Guided Test-Time Training
- URL: http://arxiv.org/abs/2402.00068v3
- Date: Tue, 19 Nov 2024 05:08:44 GMT
- Title: Adapting Amidst Degradation: Cross Domain Li-ion Battery Health Estimation via Physics-Guided Test-Time Training
- Authors: Yuyuan Feng, Guosheng Hu, Xiaodong Li, Zhihong Zhang,
- Abstract summary: Health modeling of lithium-ion batteries (LIBs) is crucial for safe and efficient energy management and carries significant socio-economic implications.
We introduce a practical Test-Time Training framework, BatteryTTT, which adapts the model continually using each target data (UTD) collected amidst degradation.
To fully utilize each UTD, BatteryTTT integrates the inherent physical laws of modern LIBs into self-supervised learning, termed Physcics-Guided Test-Time Training.
- Score: 19.606703130917325
- License:
- Abstract: Health modeling of lithium-ion batteries (LIBs) is crucial for safe and efficient energy management and carries significant socio-economic implications. Although Machine Learning (ML)-based State of Health (SOH) estimation methods have made significant progress in accuracy, the scarcity of high-quality LIB data remains a major obstacle. Existing transfer learning methods for cross-domain LIB SOH estimation have significantly alleviated the labeling burden of target LIB data, however, they still require sufficient unlabeled target data (UTD) for effective adaptation to the target domain. Collecting this UTD is challenging due to the time-consuming nature of degradation experiments. To address this issue, we introduce a practical Test-Time Training framework, BatteryTTT, which adapts the model continually using each UTD collected amidst degradation, thereby significantly reducing data collection time. To fully utilize each UTD, BatteryTTT integrates the inherent physical laws of modern LIBs into self-supervised learning, termed Physcics-Guided Test-Time Training. Additionally, we explore the potential of large language models (LLMs) in battery sequence modeling by evaluating their performance in SOH estimation through model reprogramming and prefix prompt adaptation. The combination of BatteryTTT and LLM modeling, termed GPT4Battery, achieves state-of-the-art generalization results across current LIB benchmarks. Furthermore, we demonstrate the practical value and scalability of our approach by deploying it in our real-world battery management system (BMS) for 300Ah large-scale energy storage LIBs.
Related papers
- Improving Biomedical Entity Linking with Retrieval-enhanced Learning [53.24726622142558]
$k$NN-BioEL provides a BioEL model with the ability to reference similar instances from the entire training corpus as clues for prediction.
We show that $k$NN-BioEL outperforms state-of-the-art baselines on several datasets.
arXiv Detail & Related papers (2023-12-15T14:04:23Z) - Semi-Supervised Class-Agnostic Motion Prediction with Pseudo Label
Regeneration and BEVMix [59.55173022987071]
We study the potential of semi-supervised learning for class-agnostic motion prediction.
Our framework adopts a consistency-based self-training paradigm, enabling the model to learn from unlabeled data.
Our method exhibits comparable performance to weakly and some fully supervised methods.
arXiv Detail & Related papers (2023-12-13T09:32:50Z) - Semi-Federated Learning: Convergence Analysis and Optimization of A
Hybrid Learning Framework [70.83511997272457]
We propose a semi-federated learning (SemiFL) paradigm to leverage both the base station (BS) and devices for a hybrid implementation of centralized learning (CL) and FL.
We propose a two-stage algorithm to solve this intractable problem, in which we provide the closed-form solutions to the beamformers.
arXiv Detail & Related papers (2023-10-04T03:32:39Z) - A Mapping Study of Machine Learning Methods for Remaining Useful Life
Estimation of Lead-Acid Batteries [0.0]
State of Health (SoH) and Remaining Useful Life (RUL) contribute to enhancing predictive maintenance, reliability, and longevity of battery systems.
This paper presents a mapping study of the state-of-the-art in machine learning methods for estimating the SoH and RUL of lead-acid batteries.
arXiv Detail & Related papers (2023-07-11T10:41:41Z) - DIICAN: Dual Time-scale State-Coupled Co-estimation of SOC, SOH and RUL
for Lithium-Ion Batteries [6.930255986517943]
A state-coupled co-estimation method named Deep Inter and Intra-Cycle Attention Network (DIICAN) is proposed in this paper.
The DIICAN method is validated on the Oxford battery dataset.
arXiv Detail & Related papers (2022-10-20T14:42:20Z) - Dynaformer: A Deep Learning Model for Ageing-aware Battery Discharge
Prediction [2.670887944566458]
We introduce a novel Transformer-based deep learning architecture which is able to simultaneously infer the ageing state from a limited number of voltage/current samples.
Our experiments show that the trained model is effective for input current profiles of different complexities and is robust to a wide range of degradation levels.
arXiv Detail & Related papers (2022-06-01T15:31:06Z) - Hybrid physics-based and data-driven modeling with calibrated
uncertainty for lithium-ion battery degradation diagnosis and prognosis [6.7143928677892335]
Lithium-ion batteries (LIBs) are key to promoting electrification in the coming decades.
Inadequate understanding of LIB degradation is an important bottleneck that limits battery durability and safety.
Here, we propose hybrid physics-based and data-driven modeling for online diagnosis and prognosis of battery degradation.
arXiv Detail & Related papers (2021-10-25T11:14:12Z) - Machine learning pipeline for battery state of health estimation [3.0238880199349834]
We design and evaluate a machine learning pipeline for estimation of battery capacity fade.
The pipeline estimates battery SOH with an associated confidence interval by using two parametric and two non-parametric algorithms.
When deployed on cells operated under the fast-charging protocol, the best model achieves a root mean squared percent error of 0.45%.
arXiv Detail & Related papers (2021-02-01T13:50:56Z) - Towards an Automatic Analysis of CHO-K1 Suspension Growth in
Microfluidic Single-cell Cultivation [63.94623495501023]
We propose a novel Machine Learning architecture, which allows us to infuse a neural deep network with human-powered abstraction on the level of data.
Specifically, we train a generative model simultaneously on natural and synthetic data, so that it learns a shared representation, from which a target variable, such as the cell count, can be reliably estimated.
arXiv Detail & Related papers (2020-10-20T08:36:51Z) - Universal Battery Performance and Degradation Model for Electric
Aircraft [52.77024349608834]
Design, analysis, and operation of electric vertical takeoff and landing aircraft (eVTOLs) requires fast and accurate prediction of Li-ion battery performance.
We generate a battery performance and thermal behavior dataset specific to eVTOL duty cycles.
We use this dataset to develop a battery performance and degradation model (Cellfit) which employs physics-informed machine learning.
arXiv Detail & Related papers (2020-07-06T16:10:54Z) - Deep Learning for Virtual Screening: Five Reasons to Use ROC Cost
Functions [80.12620331438052]
deep learning has become an important tool for rapid screening of billions of molecules in silico for potential hits containing desired chemical features.
Despite its importance, substantial challenges persist in training these models, such as severe class imbalance, high decision thresholds, and lack of ground truth labels in some datasets.
We argue in favor of directly optimizing the receiver operating characteristic (ROC) in such cases, due to its robustness to class imbalance.
arXiv Detail & Related papers (2020-06-25T08:46:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.