Early Quality Classification and Prediction of Battery Cycle Life in Production Using Machine Learning

Stock, Sandro; Pohlmann, Sebastian; Günter, Florian J.; Hille, Lucas; Hagemeister, Jan; Reinhart, Gunther

doi:10.1016/j.est.2022.104144

Cited by 41 publications

(12 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Weng et al 188 extracted resistance at a low SoC as a feature, which realized very early stage lifetime prediction after manufacturing for NMC batteries. Stock et al 189 also managed to predict the lifetime of NMC batteries at an early stage with features extracted from electrochemical impedance spectroscopy (EIS) and cycling data. These two works show prospects for EoL point prediction with the resistance-based feature extraction method.…”

Section: Eol Point Predictionmentioning

confidence: 99%

Health prognostics for lithium-ion batteries: mechanisms, methods, and prospects

Che

Lin

et al. 2023

Energy Environ. Sci.

116

View full text Add to dashboard Cite

show abstract

Section: Eol Point Predictionmentioning

confidence: 99%

Health prognostics for lithium-ion batteries: mechanisms, methods, and prospects

Che

Lin

et al. 2023

Energy Environ. Sci.

116

View full text Add to dashboard Cite

show abstract

“…Finally, the mean value, standard deviation (STD) and root mean square (RMS) are applied for each segment. Machine learning is frequently used for long-term data analysis for classification, detection, prognosis, etc., [16][17][18][19][20][21][22][23][24][25][26][27]. In this case, unsupervised classification, i.e., clustering, is required because every machine works in different conditions, and labeling data is not an easy task.…”

Section: State Of the Artmentioning

confidence: 99%

Application of Machine Learning Tools for Long-Term Diagnostic Feature Data Segmentation

et al. 2022

View full text Add to dashboard Cite

In this paper, a novel method for long-term data segmentation in the context of machine health prognosis is presented. The purpose of the method is to find borders between three data segments. It is assumed that each segment contains the data that represent different statistical properties, that is, a different model. It is proposed to use a moving window approach, statistical parametrization of the data in the window, and simple clustering techniques. Moreover, it is found that features are highly correlated, so principal component analysis is exploited. We find that the probability density function of the first principal component may be sufficient to find borders between classes. We consider two cases of data distributions, Gaussian and α-stable, belonging to the class of non-Gaussian heavy-tailed distributions. It is shown that for random components with Gaussian distribution, the proposed methodology is very effective, while for the non-Gaussian case, both features and the concept of moving window should be re-considered. Finally, the procedure is tested for real data sets. The results provided here may be helpful in understanding some specific cases of machine health prognosis in the presence of non-Gaussian noise. The proposed approach is model free, and thus it is universal. The methodology can be applied for any long-term data where segmentation is crucial for the data processing.

show abstract

“…In addition, parallel measurements on several test channels are often not possible due to the use of multiplexer technology, and the frequency range of more economic devices is limited to a smaller, comparatively low-frequency range. Especially for the determination of the HFR via interpolation, as shown in previous articles, [16,18,19] not only is a frequency response analyzer necessary. Also, a sufficiently high-measurement frequency is crucial to find an intersection of the measured data points with the axis representing the real impedance part.…”

Section: Introductionmentioning

confidence: 99%

“…This parameter has recently been used as one of the multiple input parameters in an artificial neural network to predict the cycle life of battery cells with varying electrolyte filling. [ 18 ] In, [ 14 ] impedance spectra were measured and the value at a measurement frequency of 1 Hz was used for the monitoring of the electrolyte wetting. Still, the different EIS‐based methods have the measurement of the impedance at quite high frequencies exclusively in common.…”

Section: Introductionmentioning

confidence: 99%

Simplified Electrochemical Approaches for Quality Determination of the Wetting Process in Lithium‐Ion Cell Production

Grundmeier

Schlüter

2023

Energy Tech

View full text Add to dashboard Cite

Electrolyte filling and wetting are safety‐relevant and time‐ and cost‐intensive processes in lithium‐ion cell production, and are hence critical process steps. Currently, only limited measurement technologies are available that would be suitable for inline monitoring and quality assurance of these process sequences. Herein, two promising electrochemical approaches for monitoring electrolyte wetting are presented, which can be utilized in low‐cost measurement devices. Starting from the introduction of a simplified impedance approach with a straightforward data evaluation, a direct current‐based method is introduced that does not require impedance equipment, and can thus be performed with standard battery cyclers. First, the extended applicability of the simplified impedance measurement is demonstrated by examining the dependence of experimental impedance results on varying electrolyte volumes, also including insufficient amounts. Subsequently, the impedance approach is transferred into the direct current method. The latter mimics impedance signals by utilizing repetitive direct current charge and discharge pulses, which are used to determine the batteries’ internal resistance during the electrolyte wetting. Both introduced approaches yield comparable results and allow the inline monitoring of the electrolyte wetting with basic equipment and with no need for demanding data evaluation.

show abstract

Early Quality Classification and Prediction of Battery Cycle Life in Production Using Machine Learning

Cited by 41 publications

References 32 publications

Health prognostics for lithium-ion batteries: mechanisms, methods, and prospects

Health prognostics for lithium-ion batteries: mechanisms, methods, and prospects

Application of Machine Learning Tools for Long-Term Diagnostic Feature Data Segmentation

Simplified Electrochemical Approaches for Quality Determination of the Wetting Process in Lithium‐Ion Cell Production

Contact Info

Product

Resources

About