With the development of electric vehicles, the demand for lithium-ion batteries has been increasing annually. Accurately estimating the State of Health (SOH) of lithium-ion batteries is crucial for their efficient and reliable use. Most of the existing research on SOH estimation is based on parameters such as current, voltage, and temperature, which are prone to fluctuations. Estimating the SOH of lithium-ion batteries based on Electrochemical Impedance Spectroscopy (EIS) and data-driven approaches has been proven effective. In this paper, we explore a novel SOH estimation model for lithium batteries based on EIS and Convolutional Neural Network (CNN)-Vision Transformer (VIT). The EIS data is treated as a grayscale image, eliminating the need for manual feature extraction and simultaneously capturing both local and global features in the data. To validate the effectiveness of the proposed model, a series of simulation experiments are conducted, comparing it with various traditional machine learning models in terms of Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R²). The simulation results demonstrate that the proposed model performs best overall in the testing dataset at three different temperatures. This confirms that the model can accurately and stably estimate the SOH of lithium-ion batteries without requiring manual feature extraction and knowledge of battery aging temperature.

Battery aging is an inevitable macroscopic phenomenon in the use of the battery, which is characterized by capacity decline and power reduction. If the charging and discharging strategy does not adjust with the aging state, it is easy to cause battery abuse and accelerate the decline. To avoid this situation, the aging model with consideration of the battery degradation is coupled into the pseudo-two-dimensional (P2D) model. An aging effect-aware finite element model that can describe battery physical information accurately is presented in this article. The model parameters are divided into four parts: structure parameters, thermodynamic parameters, kinetic parameters, and aging parameters. The identification experiments are designed based on the characteristics of these types of parameters. The decoupling and parameter identification methods of kinetic parameters according to the response characteristics of each parameter under specific excitation, and state-of-charge (SOC) partitioned range identification technology of aging parameters is proposed and verified. Finally, the aging effect-aware model and the identification parameters are verified under constant current (CC) and different dynamic conditions with different charge rate (C-rate). The ability of the proposed model to track the aging trajectory in the whole life cycle is verified under various cycle conditions. The proposed model can be applied to aging mechanism analysis and health management from point of inner properties of the batteries.

The inconsistency of cells in the battery pack is one of the main causes of battery failure. In practical applications, the terminal voltage is an important parameter that is easy to obtain and can characterize the inconsistency of cells. In this paper, a fault diagnosis method based on piecewise dimensionality reduction and outlier identification is proposed according to the voltage inconsistency of cells in the battery pack. This method uses a piecewise aggregate approximation (PAA) algorithm with a shift factor to reduce the dimension of the cell voltage time series, after which a deletion mechanism is designed based on the clustering algorithm and outlier identification to calculate the clustering quality after deleting each cell, reflecting the deviate degree of each cell. In addition, a safety management strategy is designed based on the Z-score method, and an abnormality coefficient is set to evaluate the inconsistency of cells. The effectiveness of the proposed diagnosis method is verified by monitoring the voltage data of two real-world electric vehicles. The verification results show that the method can not only detect the inconsistency before the failure of the faulty cell in the battery pack in advance, but also reduce the risk of computational explosion caused by the voltage time series and accurately locate the faulty cell.

In recent years, the number of safety accidents in new-energy electric vehicles due to lithium-ion battery failures has been increasing, and the lithium-ion battery fault diagnosis technology is particularly important to ensure the safe operation of electric vehicles. This paper proposes a method for lithium-ion battery fault diagnosis based on the historical trajectory of lithium-ion battery remaining discharge capacity in medium and long time scales. The method first utilizes the sparrow search algorithm (SSA) to identify the parameters of the second-order equivalent circuit model of the lithium-ion battery, and then estimates the state of charge (SOC) of the lithium-ion battery using the extended Kalman filter (EKF). The remaining discharge capacity is estimated according to the SOC, and finally the feature vectors are used to diagnose the faults using box plots on the medium and long time scales. Experimental results verify that the root mean squared error (RSME) and mean absolute error (MAE) of the proposed SOC estimation method are 0.0049 and 0.0034, respectively. This method can accurately identify the faulty single cell in a battery pack with low-capacity single cells and promptly detect any abnormalities in the single cell when a micro-short circuit fault occurs.

Short circuit failure is one of the triggers for thermal runaway of lithium-ion batteries, which can lead to serious safety issues. This paper attempts to estimate the short-circuit resistance of the cell using the mean difference model and relies on the estimated results to make a quantitative analysis of short-circuit fault. To achieve this goal, a combination of forgetting factor recursive least squares and extended kalman filter is used to estimate the average open-circuit voltage within the battery pack. Subsequently, since both the open-circuit voltage (OCV) and intrinsic mode function (IMF₀) components reflect the low-frequency characteristics of battery voltage, we propose a new method based on the variational modal decomposition to extract the differential open-circuit voltage of the battery, and finally make an estimate of the short-circuit resistance after obtaining OCV of the battery using the idea of the mean difference model (MDM). In addition, the effectiveness of the proposed method is verified under different degrees of short-circuit faults by connecting different resistors to the series battery pack.

This study focuses on the safety and reliability issues of lithium-ion batteries, proposing a fault diagnosis strategy that leverages dual-feature extraction from both the time and frequency domains. Additionally, by modifying the traditional autoencoder, the study proposes a feature-guided autoencoder as an unsupervised model for extracting features in the time domain. Initially, wavelet packet decomposition and its energy-denoising treatment are employed to refine fault information within battery voltage signals. Subsequently, the reconstruction error outputted by the Feature-Guided Autoencoder is utilized as the time-domain fault feature, while the cosine similarity of the energy of signals in various frequency bands obtained after wavelet packet decomposition serves as the frequency-domain fault feature. Ultimately, this article selects the Isolation Forest algorithm for two-dimensional outlier detection of time and frequency features. Experimental results demonstrate that the feature-guided autoencoder proposed in this study not only enhances the sensitivity of time-domain fault features compared to traditional autoencoders and their variants but also optimizes issues related to training time and computational load. The effectiveness of the proposed dual-feature fault diagnosis method in both the time and frequency domains is validated through data from two actual vehicles, showing superior early fault detection capability relative to single-feature fault diagnosis methods.