Dynamic Prediction of Proton-Exchange Membrane Fuel Cell Degradation Based on Gated Recurrent Unit and Grey Wolf Optimization DOI Creative Commons

Xiangdong Wang,

Zerong Huang,

Daxing Zhang

и другие.

Energies, Год журнала: 2024, Номер 17(23), С. 5855 - 5855

Опубликована: Ноя. 22, 2024

This paper addresses the challenge of degradation prediction in proton-exchange membrane fuel cells (PEMFCs). Traditional methods often struggle to balance accuracy and complexity, particularly under dynamic operational conditions. To overcome these limitations, this study proposes a data-driven approach based on gated recurrent unit (GRU) neural network, optimized by grey wolf optimizer (GWO). The integration GWO automates hyperparameter tuning process, enhancing predictive performance GRU network. proposed GWO-GRU method was validated utilizing actual PEMFC data load results demonstrate that achieves superior compared other standard methods. offers practical solution for online prediction, providing stable accurate forecasting systems environments.

Язык: Английский

A Joint Prediction of the State of Health and Remaining Useful Life of Lithium-Ion Batteries Based on Gaussian Process Regression and Long Short-Term Memory DOI Open Access

Xing Luo,

Yuanyuan Song,

Wenxie Bu

и другие.

Processes, Год журнала: 2025, Номер 13(1), С. 239 - 239

Опубликована: Янв. 15, 2025

To comprehensively evaluate the current and future aging states of lithium-ion batteries, namely their State Health (SOH) Remaining Useful Life (RUL), this paper proposes a joint prediction method based on Gaussian Process Regression (GPR) Long Short-Term Memory (LSTM) networks. First, health features (HFs) are extracted from partial charging data. Subsequently, these fed into GPR model for SOH estimation, generating predictions. Finally, estimated values initial cycle to start point (SP) input LSTM network in order predict trajectory, identify End (EOL), infer RUL. Validation Oxford Battery Degradation Dataset demonstrates that achieves high accuracy both estimation RUL prediction. Furthermore, proposed approach can directly utilize one or more without requiring dimensionality reduction feature fusion. It also enables at early stages battery’s lifecycle, providing an efficient reliable solution battery management. However, study is data small-capacity batteries does not yet encompass applications large-capacity high-temperature scenarios. Future work will focus expanding scope validating model’s performance real-world systems, driving its application practical engineering

Язык: Английский

Процитировано

1
Electric Motor Vibration Signal Classification Using Wigner–Ville Distribution for Fault Diagnosis DOI Creative Commons
Jian-Da Wu, Wenjun Luo, Kai‐Chao Yao

и другие.

Sensors, Год журнала: 2025, Номер 25(4), С. 1196 - 1196

Опубликована: Фев. 15, 2025

Noise and vibration signal classification can be applied to fault diagnosis in mechanical electronic systems such as electric vehicles. Traditional technology uses time frequency domain characteristics the identification basis. This study proposes a technique for visualizing sound signals using Wigner-Ville distribution (WVD) method extract artificial neural networks A brushless motor is used machinery power source verify feasibility of this classify different characteristics. In experimental work, six states various revolutions were deliberately designed measuring signals. The imaged WVD analysis Through method, data converted, YOLO (you only look once) deep coiling machine identify images. Wagener parameters recognition rates are discussed, thereby improving accurate diagnostic capabilities. research provides that accurately performed without dismantling motor. proposed approach improve reliability stability applications.

Язык: Английский

Процитировано

0
A hybrid approach for lithium-ion battery remaining useful life prediction using signal decomposition and machine learning DOI Creative Commons
Yibiao Fan, Ziyong Lin, Fan Wang

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 10, 2025

Lithium-ion batteries are widely used in many fields, and accurate prediction of their remaining useful life (RUL) was crucial for effective battery management safety assurance. In order to solve the problem reduced RUL accuracy caused by local capacity regeneration phenomenon during degradation, this paper proposed a novel method, which combined complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) technique an innovative hybrid strategy that integrated support vector regression (SVR) long short-term memory (LSTM) networks. First, CEEMDAN decompose data into high-frequency low-frequency components, thereby reducing impact regeneration. Subsequently, SVR model predicted component characterized main degradation trend, contained features using LSTM network optimized sparrow search algorithm (SSA). Finally, final obtained combining predictions two models. Experimental results on NASA public datasets showed method significantly outperformed existing methods: RMSE methods were all less than 0.0086 Ah, MAE 0.0060 R2 values higher 0.96, errors controlled within one cycle. This gave full play complementary advantages provided reliable solution lithium-ion batteries.

Язык: Английский

Процитировано

0
Repurposing Second-Life EV Batteries to Advance Sustainable Development: A Comprehensive Review DOI Creative Commons
Muhammad Nadeem Akram,

Walid Abdul‐Kader

Batteries, Год журнала: 2024, Номер 10(12), С. 452 - 452

Опубликована: Дек. 20, 2024

While lithium-ion batteries (LIBs) have pushed the progression of electric vehicles (EVs) as a viable commercial option, they introduce their own set issues regarding sustainable development. This paper investigates how using end-of-life LIBs in stationary applications can bring us closer to meeting development goals (SDGs) highlighted by United Nations. We focus on this practice support three these goals, namely Goal 7: Affordable and Clean Energy, 12: Responsible Consumption Production, 13: Climate Action. present literature review that details aging mechanisms LIBs, battery degradation, state charge, health, depth discharge, remaining useful life, management systems. Then, we thoroughly examine environmental economic benefits second-life EV align with SDGs. Our summarizes most relevant research aging, giving foundation for further allowing effective legislation be written around EVs. Additionally, our examination motivates initiatives practices, helping both corporations legislators orient ideals towards

Язык: Английский

Процитировано

2
Dynamic Prediction of Proton-Exchange Membrane Fuel Cell Degradation Based on Gated Recurrent Unit and Grey Wolf Optimization DOI Creative Commons

Xiangdong Wang,

Zerong Huang,

Daxing Zhang

и другие.

Energies, Год журнала: 2024, Номер 17(23), С. 5855 - 5855

Опубликована: Ноя. 22, 2024

This paper addresses the challenge of degradation prediction in proton-exchange membrane fuel cells (PEMFCs). Traditional methods often struggle to balance accuracy and complexity, particularly under dynamic operational conditions. To overcome these limitations, this study proposes a data-driven approach based on gated recurrent unit (GRU) neural network, optimized by grey wolf optimizer (GWO). The integration GWO automates hyperparameter tuning process, enhancing predictive performance GRU network. proposed GWO-GRU method was validated utilizing actual PEMFC data load results demonstrate that achieves superior compared other standard methods. offers practical solution for online prediction, providing stable accurate forecasting systems environments.

Язык: Английский

Процитировано

1