Skip to content
DraconiticResearch
Search Sources API
178,033 studies31 sourcesUpdated 26 min ago
Peer-reviewedCC BY 4.0Batteries

Remaining Useful Life Prediction of Lithium-Ion Batteries Based on Artificial Neural Network-Supported Wiener Process with Random Effects

  • Xiaoyan Sun1
  • Shengjin Tang2
  • Fengchao Zhu1
  • Wenke Yang1
  • Xiaodong Xu2
  • Lifeng Wu3
  1. 1Department of Communication Engineering, PLA Rocket Force University of Engineering, Xi’an 710025, China
  2. 2Department of Mechanical Engineering, PLA Rocket Force University of Engineering, Xi’an 710025, China
  3. 3Information Engineering College, Capital Normal University, Beijing 100048, China
Open at sourceDOICite

Abstract

Among various data-driven approaches for remaining useful life (RUL) prediction, Wiener process-based degradation models are interpretable and quantify uncertainty. However, existing methods that combine artificial neural networks (ANNs) with the Wiener process have not yet fully exploited the modeling power of neural networks or the analytical tractability of stochastic processes. To overcome this limitation, this paper proposes an ANN-supported Wiener process with random effects for RUL prediction. Specifically, a bias-free four-layer neural network is constructed to characterize the latent nonlinear degradation trajectory, while the drift coefficient is modeled as a random variable to capture unit-to-unit variability. An analytical expression for the time derivative of the network output is derived, facilitating the closed-form solution of the probability density function (PDF) of RULs within the first passage time framework. A training strategy based on the Levenberg–Marquardt algorithm is developed for efficient parameter estimation, and the Akaike information criterion is used to select the optimal network architecture. The proposed method is validated using two lithium-ion battery degradation datasets. Experimental results verify that the proposed method exhibits superior performance to traditional nonlinear degradation models in terms of both fitting performance and RUL prediction accuracy, with the advantages becoming more pronounced in long-term prediction scenarios.

Related

  1. Physics-Informed Explainable Machine Learning for Hybrid State of Health and Remaining Useful Life Estimation of Lithium-Ion Batteries
    Plamen Stanchev, Nikolay Hinov
    BatteriesPeer-reviewedCC BY 4.0Electrochemistry & energyCrossref
  2. A Study on Lithium-Ion Battery Health Estimation and Remaining Life Prediction Based on Real-World Operational Data
    Jiwei Wang, Wenpeng Si, Masrafe Alam Munna +2
    BatteriesPeer-reviewedCC BY 4.0Full textElectrochemistry & energyCrossrefDOAJ
  3. A Compression Force Prediction Model for Mechanically Constrained Lithium-Ion Batteries
    Jun Yin, Christoph Drießen, Maximilian Schinagl +3
    BatteriesPeer-reviewedCC BY 4.0Electrochemistry & energyCrossref
  4. Capacity and SOH Prediction of Lithium-Ion Batteries Using Various Mathematical Forms of EIS with Neural Networks
    Hakeem Thomas, Mark H. Weatherspoon
    BatteriesPeer-reviewedCC BY 4.0Electrochemistry & energyCrossref
  5. How to Discover New Electrolyte Additives for Lithium Batteries: A Computational Roadmap
    Ilya V. Chepkasov, Alexey S. Galushko, Mikhail N. Khrizanforov +2
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv

Cite

BibTeXRIS
BibTeX
@article{sun2026remaining,
  title = {{Remaining Useful Life Prediction of Lithium-Ion Batteries Based on Artificial Neural Network-Supported Wiener Process with Random Effects}},
  author = {Xiaoyan Sun and Shengjin Tang and Fengchao Zhu and Wenke Yang and Xiaodong Xu and Lifeng Wu},
  journal = {Batteries},
  year = {2026},
  month = nov,
  doi = {10.3390/batteries12110459},
  url = {https://www.mdpi.com/2313-0105/12/11/459},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Remaining Useful Life Prediction of Lithium-Ion Batteries Based on Artificial Neural Network-Supported Wiener Process with Random Effects
AU  - Xiaoyan Sun
AU  - Shengjin Tang
AU  - Fengchao Zhu
AU  - Wenke Yang
AU  - Xiaodong Xu
AU  - Lifeng Wu
PY  - 2026
DA  - 2026/11/03
JO  - Batteries
DO  - 10.3390/batteries12110459
UR  - https://www.mdpi.com/2313-0105/12/11/459
AB  - Among various data-driven approaches for remaining useful life (RUL) prediction, Wiener process-based degradation models are interpretable and quantify uncertainty. However, existing methods that combine artificial neural networks (ANNs) with the Wiener process have not yet fully exploited the modeling power of neural networks or the analytical tractability of stochastic processes. To overcome this limitation, this paper proposes an ANN-supported Wiener process with random effects for RUL prediction. Specifically, a bias-free four-layer neural network is constructed to characterize the latent nonlinear degradation trajectory, while the drift coefficient is modeled as a random variable to capture unit-to-unit variability. An analytical expression for the time derivative of the network output is derived, facilitating the closed-form solution of the probability density function (PDF) of RULs within the first passage time framework. A training strategy based on the Levenberg–Marquardt algorithm is developed for efficient parameter estimation, and the Akaike information criterion is used to select the optimal network architecture. The proposed method is validated using two lithium-ion battery degradation datasets. Experimental results verify that the proposed method exhibits superior performance to traditional nonlinear degradation models in terms of both fitting performance and RUL prediction accuracy, with the advantages becoming more pronounced in long-term prediction scenarios.
SN  - 2313-0105
ER  -