Our proposed method proves to achieve future capacity prediction performance. The best relative error values for the three target batteries using the proposed method were 6.96 %, 0.60 %, and 5.95 %, respectively. The results show that our proposed method is suitable for future capacity prediction and online RUL prediction of Li-ion batteries.
Four batteries from the Toyota data set were used to demonstrate the prediction's performance. Our proposed method proves to achieve future capacity prediction performance. The best relative error values for the three target batteries using the proposed method were 6.96 %, 0.60 %, and 5.95 %, respectively.
The results show that our proposed method is suitable for future capacity prediction and online RUL prediction of Li-ion batteries. Therefore, the proposed method can be applied as battery maintenance to provide early warning of battery failure.
This paper presents an online predicting future capacity method based on transfer learning with the BiLSTM-AM and SVR models using the EEMD algorithm to decompose the normalized capacity. Four batteries from the Toyota data set were used to demonstrate the prediction's performance.
Predicting future battery capacity and its RUL is a challenging problem in battery health diagnosis and management applications.
The proposed method consists of integrating an ensemble empirical mode decomposition algorithm, a support vector regression model, and a bidirectional long short-term memory with attention mechanism model to predict the state of health (SOH), where SOH is the battery cycle life and discharge capacity measured in number of cycles.
DOI: 10.1080/15435075.2024.2386070 Corpus ID: 271631594; A coarse-to-fine ensemble method for capacity prediction of lithium-ion batteries in production @article{Zhang2024ACE, …
This paper proposes a coarse-to-fine ensemble learning framework using LightGBM regression algorithm to predict battery capacity. The framework uses raw statistical …
Herein, a capacity prediction method for lithium‐ion batteries based on …
This paper presents a novel BTMS based on a liquid cooling method with liquid metal, which uses liquid metal as a coolant to achieve better cooling capacity and energy …
Once battery capacity reaches EOL, its capacity declines faster, potentially leading to impaired or even catastrophic operation. One of the topics in battery management …
1 · Insufficient capture of feature information will also lead to low prediction accuracy of the model. Aiming at the above problems, a method for estimating the capacity of lithium-ion …
To address the above issues, this study establishes an improved extreme …
Although the prediction errors of batteries 3–7 and 3–8 in Fig. 13(b) and (e) are more than 8% due to the influence of the subsequent battery capacity increase and decrease, …
This paper proposes a coarse-to-fine ensemble learning framework using …
Based on the new energy vehicle battery management system, the article constructs a new battery temperature prediction model, SOA-BP neural network, using BP …
The results show that the battery aging information extracted during the partial charging process is closely related to battery capacity degradation, and the proposed capacity …
Measuring capacity in the grading process is an important step in battery production. The traditional capacity acquisition method requires considerable time and energy consumption; …
A capacity prediction method is proposed for a production line to reduce the battery production …
A capacity prediction method is proposed for a production line to reduce the battery production cost, which can reduce the capacity measurement time by half. The artificial intelligence …
The results show that the battery aging information extracted during the …
Experimental results demonstrate that the proposed method accurately estimates the lithium-ion battery capacity, with values of RMSE, MAPE, and MD-MAPE of only 0.0220, …
Abstract: As one of the most attractive energy storage devices, capacity prediction of lithium-ion batteries is significant to improve the safe availability of new energy …
Battery energy storage systems (BESS) will have a CAGR of 30 percent, and the GWh required to power these applications in 2030 will be comparable to the GWh needed …
The traditional capacity acquisition method requires considerable time and energy consumption; therefore, an accurate capacity estimation is crucial in reducing production costs. Herein, a …
From the prediction capability of the overall aging trajectory trend of lithium-ion batteries, the proposed prediction method was further verified to have good prediction …
1 · Insufficient capture of feature information will also lead to low prediction accuracy of …
This paper presents a novel BTMS based on a liquid cooling method with liquid metal, which uses liquid metal as a coolant to achieve better cooling capacity and energy efficiency.
From the prediction capability of the overall aging trajectory trend of lithium-ion batteries, the proposed prediction method was further verified to have good prediction accuracy compared to the traditional LSTM and …
The traditional capacity acquisition method requires considerable time and energy consumption; therefore, an accurate capacity estimation is crucial in reducing …
Capacity prediction of lithium-ion batteries represents an important function of battery management systems. Conventional machine learning-based methods for capacity …
Herein, a capacity prediction method for lithium‐ion batteries based on improved random forest (RF) is proposed. This method extracts features from the voltage data …
Abstract: As one of the most attractive energy storage devices, capacity …
To address the above issues, this study establishes an improved extreme learning machine (ELM) model for predicting battery capacity in the manufacturing process, …