Machine Learning-Based Data-Driven Fault
This paper provides a comprehensive review exclusively on the state-of-the-art ML-based data-driven fault detection/diagnosis techniques to provide a ready reference and direction to the
A K-Value Dynamic Detection Method Based on Machine
A K-Value Dynamic Detection Method Based on Machine Learning for Lithium-Ion Battery Manufacturing Data-driven analysis on thermal effects and temperature changes of lithium-ion battery; Dynamic battery cell model and state of charge estimation;
A method for estimating lithium-ion battery state of health
6 天之前· Lithium-ion batteries (LIB) have become increasingly prevalent as one of the crucial energy storage systems in modern society and are regarded as a key technology for achieving sustainable development goals [1, 2].LIBs possess advantages such as high energy density, high specific energy, low pollution, and low energy consumption [3], making them the preferred
Comprehensive fault diagnosis of lithium-ion batteries: An
Xu et al. (2024b) proposed a multi-objective nonlinear fault detection observer for lithium-ion batteries, developing a high-precision, However, the ability of OLE in quantifying the orbital divergence depends on the stability and continuity of dynamic systems. In discrete battery systems, the difficulty in determining the initial state
Enhanced Wavelet Transform Dynamic Attention Transformer
A Transformer model with a wavelet transform dynamic attention mechanism (WADT) that focuses adaptively on the most informative parts of the battery data to enhance the anomaly detection accuracy and a deep learning model with an improved Transformer architecture tailored for the complex dynamics of battery data time series. Rapid
Enhanced Wavelet Transform Dynamic Attention Transformer
Model for Recycled Lithium-Ion Battery Anomaly Detection Xin Liu 1, *, Haihong Huang 1,†, Wenjing Chang 2, Y ongqi Cao 1 and Y uhang Wang 1 1 School of Electrical Engineering and Automation
DGL-STFA: Predicting lithium-ion battery health with dynamic
The DGL-STFA framework predicts the SOH of lithium-ion batteries by capturing dynamic spatial–temporal dependencies. The dynamic graph learning approach constructs a
Nonlinear Fault Detection and Isolation for a Lithium-Ion Battery
Lithium-ion batteries are a growing source for electric power, but must be maintained within acceptable operating conditions to ensure efficiency and reliability. Therefore, a robust fault detection and isolation scheme is required that is sensitive enough to determine when sensor or actuator faults present a threat to the health of the battery. A scheme suitable for a hybrid
Research on Early Multi-fault Diagnosis of Lithium Battery Under
The frequent occurrence of battery pack failures brings a great threat to the development of electric vehicles. Battery pack faults are generally multiple and diverse and have similar fault characteristics, which are difficult to distinguish and detect, and are not conducive to fault diagnosis and classification. Therefore, this paper proposes a new sensor connection topology
Realistic fault detection of li-ion battery via dynamical deep
Accurate evaluation of Li-ion battery (LiB) safety conditions can reduce unexpected cell failures, facilitate battery deployment, and promote low-carbon economies.
Enhanced Wavelet Transform Dynamic Attention Transformer
Transformer Model For Lithium-ion Battery Anomaly Detection Xin Liu, Haihong Huang Senior Member, IEEE Abstract In the context of rapid advancements in electric vehicle (EV) technology, the safety and reliability of lithium-ion (Li) batteries, non-stationary dynamic changes of battery data [18], [19]. This is because the complexity of
Anomaly Detection Method for Lithium-Ion Battery Cells Based on
Abnormalities in individual lithium-ion batteries can cause the entire battery pack to fail, thereby the operation of electric vehicles is affected and safety accidents even occur in severe cases.
Enhanced Wavelet Transform Dynamic Attention Transformer
The technique rotates the battery pack voltage sequence into a new coordinate space through linear combination, while the detection metrics of square prediction errors and
A K-Value Dynamic Detection Method Based on Machine
A K-Value Dynamic Detection Method Based on Machine Learning for Lithium-Ion Battery Manufacturing. June 2023; During the manufacturing process of the lithium-ion battery, metal foreign matter
Lithium plating detection using dynamic electrochemical
This paper proposes a lithium plating detection method for lithium-ion batteries that can be applied in real time, during the charging procedure. It is based on the impedance
Model-based thermal anomaly detection for lithium-ion batteries
Motivated by this, a model-based strategy of anomaly detection of thermal parameters for lithium-ion-batteries is presented in this paper. The algorithm is based on a multiple-model adaptive estimation framework. Firstly, an equivalent-circuit-model-based electrothermal model is proposed to describe battery dynamic behaviors. Then, a
Internal short circuit mechanisms, experimental approaches and
Lithium-ion batteries (LIBs) have the advantages of high energy/power densities, low self-discharge rate, and long cycle life, and thus are widely used in electric vehicles (EVs).
Adaptive fault detection for lithium-ion battery combining
In the literature, the battery faults detection approach is mainly divided into three types: knowledge-based, model-based, and data-driven approaches [7, 8].Knowledge-based method is to use prior knowledge or expert experience to establish a fault database, which will be improved through long-term data accumulation, and battery faults can be detected and
Detecting Electric Vehicle Battery Failure via Dynamic-VAE
dataset including cleaned battery-charging data from hundreds of vehicles. We then formulate battery failure detection as an outlier detection problem, and propose a new algorithm named Dynamic-VAE based on dynamic system and variational autoencoders. We validate the performance of our proposed algorithm against
Lithium Plating Detection Based on
Lithium plating, induced by fast charging and low-temperature charging, is one of the reasons for capacity fading and causes safety problems for lithium-ion batteries.
Enhanced Wavelet Transform Dynamic Attention
The dynamic attention mechanism uses wavelet transform. It focuses adaptively on the most informative parts of the battery data to enhance the anomaly detection accuracy. We also developed a deep learning model
A new on-line method for lithium plating detection in lithium-ion batteries
This paper proposes a comprehensive seven-step methodology for laboratory characterization of Li-ion batteries, in which the battery''s performance parameters are determined and their dependence on the operating conditions are obtained, and a novel hybrid procedure for parameterizing the batteries'' equivalent electrical circuit (EEC), which is used to emulate the
A K-Value Dynamic Detection Method Based on Machine Learning
Based on comparing the screening effect of different machine learning algorithms for the production data of lithium-ion cells, this paper proposes a K-value dynamic
Online health prognosis for lithium-ion batteries under dynamic
Lithium-ion batteries are a key power sources for electric vehicles, offering high energy density, low self-discharge rate, and long cycle life [1, 2].However, they suffer from performance degradation over time, raising concerns about safety risks such as electrolyte leakage and thermal runaway accidents [[3], [4], [5]].Accurate state of health (SOH) estimation
(PDF) Abnormal State Detection in Lithium-ion Battery
The method starts with a Dynamic Frequency Fourier Transform module, which dynamically captures the frequency characteristics of time series data across three scales, incorporating a memory
Progress and challenges in ultrasonic technology for state
Voltage profile reconstruction and state of health estimation for lithium-ion batteries under dynamic working conditions. Energy (2023) In situ detection of lithium-ion batteries by ultrasonic technologies. Energy Storage Mater. (2023) S. Dayani et al. Multi-level X-ray computed tomography (XCT) investigations of commercial lithium-ion
A Review of Lithium-Ion Battery Fault
He, H. Fault Detection and Isolation for Lithium-Ion Battery System Using Structural Analysis and Sequential Residual Generation. In Proceedings of the ASME 7th annual
A Review of Non-Destructive Testing for Lithium
In addition to lithium-ion batteries, we have summarized the non-destructive testing methods for lithium metal batteries, including X-ray CT detection and NMR detection. Ultrasonic testing (UT) has become an effective
A K -Value Dynamic Detection Method Based on
Based on comparing the screening effect of different machine learning algorithms for the production data of lithium-ion cells, this paper proposes a K-value dynamic screening algorithm for the cell production line
DGL-STFA: Predicting lithium-ion battery health with dynamic
The DGL-STFA framework predicts the SOH of lithium-ion batteries by capturing dynamic spatial–temporal dependencies. The dynamic graph learning approach constructs a series of time-evolving graphs that represent the interactions between health indicators at each time step. A survey of methods for time series change point detection. Knowl
Hydrogen Gas Detector for Lithium Battery
In the dynamic world of energy storage, the Hydrogen Gas Detector for Lithium Battery focus on safety within battery rooms is paramount. While lithium batteries dominate the market, it''s crucial to understand other battery types, such as
Accuracy and robust early detection of short
Accuracy and robust early detection of short-circuit faults in single-cell lithium battery Chengzhong Zhang,1,2 Hongyu Zhao,2 and Wenjie Zhang,1 1College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan 030024, PR China; 2University of Chinese Academy of Sciences, Shijingshan District, Beijing 100049, China CONTEXT & SCALE
Smiths Detection delivers effective lithium battery detection
Smiths Detection now offers reliable and accurate lithium battery detection as an option on the HI-SCAN 100100V-2is and 100100T-2is scanners, with other conventional X-ray systems to follow. Existing installations can also be upgraded on site. This is the first module from a series of smart and adaptable algorithms for the automatic detection
Progress and challenges in ultrasonic technology for state
Currently, applications of ultrasonic technology in battery defect detection primarily include foreign object defect detection, lithium plating detection, gas defect detection, wetting degree analysis, thermal runaway detection, electrode defects and dry state identification, and Solid Electrolyte Interphase (SEI) film growth recognition, among others.
6 FAQs about [Lithium battery dynamic detection]
How to detect faults in lithium-ion batteries?
Ref. presented a fault diagnosis method for lithium-ion batteries based on signal analysis and manifold learning, achieving earlier and more robust fault detection by eliminating the impact of state inconsistency and using clustering-based anomaly detection.
Can a lithium plating detection method be applied in real time?
This paper proposes a lithium plating detection method for lithium-ion batteries that can be applied in real time, during the charging procedure. It is based on the impedance analysis and it can be realized by utilizing the dynamic electrochemical impedance spectroscopy (DEIS) technique.
Is there a short circuit detection method for lithium ion batteries?
A Novel Al–Cu Internal Short Circuit Detection Method for Lithium-Ion Batteries Based on on-Board Signal Processing. J. Energy Storage 2022, 52, 104748. [ Google Scholar] [ CrossRef]
Can a DEIS method detect lithium plating in lithium-ion batteries?
Therefore, it has been validated that the proposed technique can effectively detect the lithium plating in lithium-ion batteries for several charging conditions, cell formats and chemistries. The advantages of the proposed DEIS method have been also highlighted by comparing it with the current interruption method.
Can deep learning be used for battery state monitoring & anomaly detection?
In the field of battery state monitoring and anomaly detection, researchers have proposed numerous approaches, including methods based on physical modeling as well as strategies utilizing data-driven deep learning [9, 10]. However, existing methods often fail to adequately consider the non-stationarity and complex dynamics of battery data.
Do hyperparameters affect the detection results of lithium-ion cells?
Firstly, the OCV- K dataset of lithium-ion cells, with the size of 3000 in the previous section, was used to analyze the effect of the hyperparameters on the detection results. Equations (9) and (11) show that the detection method has two hyperparameters, k and s.