A Novel Remaining Useful Life Prediction Method for Lithium-Ion Battery Based on Long Short-Term Memory Network Optimized by Improved Sparrow Search Algorithm. J. Energy Storage 2023, 61, 106645. [ Google Scholar] [ CrossRef]
At present, there are primarily two approaches for predicting the RUL of lithium-ion batteries: model-based methods and data-driven methods [ 9, 10 ]. The model-based methods approach to predicting the RUL of lithium-ion batteries involves analyzing internal physical and chemical reactions within the battery.
The current challenges and perspectives of early-stage prediction are comprehensively discussed. With the rapid development of lithium-ion batteries in recent years, predicting their remaining useful life based on the early stages of cycling has become increasingly important.
This includes the potential integration of thermal management factors into predictive models and utilizing scaled-up experiments or simulation studies to validate findings from small battery tests. A major challenge in the field of early life prediction of lithium-ion batteries is the lack of standardized test protocols.
Accurate and reliable prediction of the remaining useful life (RUL) of lithium-ion batteries (LIB) is very important for the safety of power systems. To solve the nonlinear and time-varying problems of LIB aging trajectories, an RUL prediction method based on variational mode decomposition (VMD) and integrated machine learning is proposed.
Initially, the CEEMDAN is employed to decompose the lithium-ion battery capacity degradation sequence into high-frequency and low-frequency components. For the high-frequency component, a TCN model is utilized for prediction. For the low-frequency component, the IHSSA-LSTM model is proposed for prediction.
The capacity regeneration phenomenon of lithium-ion batteries related to physicochemical aspects, temperature and load conditions during charge and discharge …
Life prediction facilitates efficient management and timely maintenance of lithium‐ion batteries. Challenges are still faced in eliminating the effects of battery temperature or state of charge …
Life prediction facilitates efficient management and timely maintenance of lithium-ion batteries. Challenges are still faced in eliminating the effects of battery temperature or state of charge (SOC) on the life indicator to …
Battery simulation models play a pivotal role in comprehending the intricacies of internal electrochemical reactions within batteries, thereby ensuring electric vehicle power systems'' …
Conventional RUL prediction methods typically rely on regression analysis, signal processing, and machine learning techniques to assess battery conditions such as …
1 · In this review, the necessity and urgency of early-stage prediction of battery life are highlighted by systematically analyzing the primary aging mechanisms of lithium-ion batteries, …
The experiment shows that the prediction results of the proposed IM-EI model accurately reflect the decay trend of battery capacity and have good prediction accuracy, …
The starting point of SOH prediction for lithium batteries was set at 60% of the total cycle time, and the SOH value of the remaining 40% of the cycle time was used as the …
Accurate prediction of the Remaining Useful Life (RUL) of lithium-ion batteries is crucial for reducing battery usage risks and ensuring the safe operation of systems.
Life prediction facilitates efficient management and timely maintenance of lithium‐ion batteries. Challenges are still faced in eliminating the effects of battery temperature …
A novel prediction method based on the support vector regression for the remaining useful life of lithium-ion batteries. Microelectron. Reliab. 85, 99–108 (2018).
Yu et al. [27] utilized multi-scale logistic regression and Gaussian process regression(GPR) to raise a predictor for SOH. Apart from the aforesaid data-driven studies, we …
Gao et al. proposed a hybrid prediction method based on PF and Support Vector Regression (SVR) for the RUL of lithium-ion batteries. The aforementioned methods offer a …
Meng et al. proposed a multi-scale learning method based on GPR and dropout Monte Carlo–gated recurrent unit to predict the RUL of lithium-ion batteries. Guo et al. ... Ma …
Remaining useful life prediction for lithium-ion batteries based on a hybrid model combining the long short-term memory and Elman neural networks
Health status prediction of lithium-ion batteries is critical for the stable operation of electrical equipment. The data-driven approach can fit the degradation laws based on the historical …
The experiment shows that the prediction results of the proposed IM-EI model accurately reflect the decay trend of battery capacity and have good prediction accuracy, …
The growing reliance on Li-ion batteries for mission-critical applications, such as EVs and renewable EES, has led to an immediate need for improved battery health and RUL …
Accurate prediction of the Remaining Useful Life (RUL) of lithium-ion batteries is crucial for reducing battery usage risks and ensuring the safe operation of systems.
Remaining useful life prediction method of lithium-ion batteries is based on variational modal decomposition and deep learning integrated approach. ... correlation …
A multi-scale fusion prediction method for lithium-ion battery capacity based on ensemble empirical mode decomposition and nonlinear autoregressive neural networks Pei …
I. Introduction. Lithium-ion (Li-ion) batteries are widely used in many fields, such as electric automobiles, unmanned aerial vehicles, portable electronic equipment, etc.Battery …
Conventional RUL prediction methods typically rely on regression analysis, signal processing, and machine learning techniques to assess battery conditions such as …