Conclusions A method for diagnosing the abnormal battery charging capacity based on EV operation data was developed in this study. By establishing offline and online diagnosis systems to monitor the charging capacity, the TR caused by overcharging can be effectively identified in time. The following are the most important findings of this study.
A statistics-based method is then used to diagnose battery charging capacity abnormity by analyzing the error distribution of large sets of data. The proposed tree-based prediction model is compared with other state-of-the-art methods and is shown to have the highest prediction accuracy. The holistic diagnosis scheme is verified using unseen data.
The calibration of the battery’s state of charge ( SOC) is inaccurate because of the inability of the battery management system (BMS) to accurately evaluate the aging of all cells. This leads to the overcharging of cells, which is one of the most common real-world causes of thermal runaway (TR) in batteries [ 5 ].
One way to directly detecting battery safety issues is by comparing the measurement of a specific external variable with a standard threshold. If the measurement exceeds the threshold, a safety issue is considered to be present. For example, if the voltage of a ternary lithium battery cell exceeds 4.2 V, it is considered overcharged.
During the actual operation of new energy electric vehicles, the battery failure in early stages is not obvious and is difficult to detect. When the malfunction worsens, the degree of abnormality in the battery will rapidly evolve, ultimately leading to safety accidents.
By comparing the absolute error of the DCI output from the GPR model to that of the actual DCI, the abnormal charging capacity could be identified. In addition, the Box–Cox and 3 were used to determine the threshold of the abnormal charging capacity in the online diagnosis model.
Detecting Abnormality of Battery Lifetime from First‐Cycle Data …
In this work, we make the first attempt to identify the lifetime abnormality of lithium-ion batteries using only the first-cycle aging data. A few-shot learning network is developed to detect the lifetime abnormality, without requiring prior knowledge of degradation mechanisms.
Learn More
A Novel Method for Lithium‐Ion Battery Fault …
In this paper, a novel fault diagnosis method for lithium-ion batteries of electric vehicles based on real-time voltage is proposed. Firstly, the voltage distribution of battery cells is confirmed in electric vehicles, and the …
Learn More
Detecting Abnormality of Battery Lifetime from First‐Cycle Data …
Early‐stage lifetime abnormality prediction is critical to prolonging the service life of a battery pack, but technically challenging due to not only the limited information to be possibly extracted in the first few cycles but also the inherently low rate of battery abnormality. In this paper, we use the few‐shot learning method to predict the lifetime abnormality of the …
Learn More
A novel battery abnormality detection method using …
Thereafter, a screening algorithm is established on top of a neural network to identify battery cells with abnormal charging behaviors. Subsequently, real-world charging profiles of EVs are utilized for validation. It is found that, compared with existing algorithms, the proposed method can achieve better accuracy when applied on real-world EVs ...
Learn More
Review of Abnormality Detection and Fault Diagnosis Methods
Electric vehicles are developing prosperously in recent years. Lithium-ion batteries have become the dominant energy storage device in electric vehicle application because of its advantages such as high power density and long cycle life. To ensure safe and efficient battery operations and to enable timely battery system maintenance, accurate and reliable …
Learn More
Anomaly Detection Method for Lithium-Ion Battery Cells Based …
The measurable parameters of new energy vehicle batteries mainly include voltage, current, and temperature, which are commonly used feature data in battery anomaly detection. Many existing studies have shown that when there are various abnormal faults in the battery, the voltage of the battery exhibits more pronounced fluctuations compared to ...
Learn More
Battery safety issue detection in real-world electric vehicles by ...
The results show that the integrated battery model can precisely predict normal battery terminal voltage, with mean-squared-errors of 1.034e−4 V 2, 7.221e−5 V 2, and …
Learn More
Battery safety issue detection in real-world electric vehicles by ...
The results show that the integrated battery model can precisely predict normal battery terminal voltage, with mean-squared-errors of 1.034e−4 V 2, 7.221e−5 V 2, and 4.612e−5 V 2 for driving, quick charging, and slow charging, respectively. The accuracy in classifying faulty and normal batteries is verified based on the operating data ...
Learn More
Battery abnormality displayed when charging with new energy
A novel battery abnormality detection method using interpretable … In this study, a novel data-driven framework for abnormality detection is developed through establishment of a neural network with interpretable modules on top of an Autoencoder using data from real EVs to recognize abnormality while charging.
Learn More
A Method for Abnormal Battery Charging Capacity …
Overcharging due to an abnormal charging capacity is one of the most common causes of thermal runaway (TR). This study proposes a method for diagnosing abnormal battery charging capacity based on electric vehicle (EV) …
Learn More
A Data-Driven Method for Battery Charging Capacity Abnormality ...
Abstract: Enabling charging capacity abnormality diagnosis is essential for ensuring battery operation safety in electric vehicle (EV) applications. In this article, a data-driven method is proposed for battery charging capacity diagnosis based …
Learn More
A Data-Driven Method for Battery Charging Capacity Abnormality ...
Enabling charging capacity abnormality diagnosis is essential for ensuring battery operation safety in electric vehicle (EV) applications. In this paper, a...
Learn More
Detection and Fault Diagnosis of High-Voltage System …
Composition of high voltage equipment for new energy vehicles 2.1. Power Battery Pack. …
Learn More
A Method for Abnormal Battery Charging Capacity Diagnosis …
Overcharging due to an abnormal charging capacity is one of the most common causes of thermal runaway (TR). This study proposes a method for diagnosing abnormal battery charging capacity based on electric vehicle (EV) data. The proposed method can obtain the fault frequency and output the corresponding state of charge (SOC) when a ...
Learn More
A novel battery abnormality detection method using …
The results show that the battery charging capacity reduces significantly with increasing time, and the capacity decreases by 21.30% and 22.61%, respectively, after 200 cycles. The maximum whole ...
Learn More
Research on improving the safety of new energy vehicles exploits ...
In addition, in order to explore the relationship between the above safety parameter changes and the charging current, the corresponding relationship between State of charge (SOC)and total charging current of battery pack (I) of the accident vehicle battery pack at the end of the life is shown in Fig. 4. A phenomenon of high current charging can be found obviously. Therefore, it …
Learn More
A novel battery abnormality detection method using interpretable ...
Thereafter, a screening algorithm is established on top of a neural network to identify battery cells with abnormal charging behaviors. Subsequently, real-world charging profiles of EVs are utilized for validation. It is found that, compared with existing algorithms, the …
Learn More
A novel battery abnormality diagnosis method using multi-scale ...
Accurate and efficient diagnosis of battery voltage abnormality is crucial for the safe operation of electric vehicles. This paper proposes an innovative battery voltage abnormality diagnosis method based on a normalized coefficient of variation in real-world electric vehicles. Vehicle and laboratory data are collected and analyzed, with joint preprocessing to improve …
Learn More
A novel battery abnormality diagnosis method using multi-scale ...
Accurate and efficient diagnosis of battery voltage abnormality is crucial for the safe operation of electric vehicles. This paper proposes an innovative battery voltage abnormality diagnosis method based on a normalized coefficient of variation in real-world electric vehicles.
Learn More
Detecting Abnormality of Battery Lifetime from …
In this work, we make the first attempt to identify the lifetime abnormality of lithium-ion batteries using only the first-cycle aging data. A few-shot learning network is developed to detect the lifetime abnormality, without …
Learn More
