The segmentation of tomographic images of the battery electrode is a crucial processing step,which will have an additional impact on the results of material characterization and electrochemical simulation.However,manu...The segmentation of tomographic images of the battery electrode is a crucial processing step,which will have an additional impact on the results of material characterization and electrochemical simulation.However,manually labeling X-ray CT images(XCT)is time-consuming,and these XCT images are generally difficult to segment with histographical methods.We propose a deep learning approach with an asymmetrical depth encode-decoder convolutional neural network(CNN)for real-world battery material datasets.This network achieves high accuracy while requiring small amounts of labeled data and predicts a volume of billions voxel within few minutes.While applying supervised machine learning for segmenting real-world data,the ground truth is often absent.The results of segmentation are usually qualitatively justified by visual judgement.We try to unravel this fuzzy definition of segmentation quality by identifying the uncertainty due to the human bias diluted in the training data.Further CNN trainings using synthetic data show quantitative impact of such uncertainty on the determination of material’s properties.Nano-XCT datasets of various battery materials have been successfully segmented by training this neural network from scratch.We will also show that applying the transfer learning,which consists of reusing a well-trained network,can improve the accuracy of a similar dataset.展开更多
The computational simulation of the manufacturing process of lithium-ion battery composite electrodes based on mechanistic models allows capturing the influence of manufacturing parameters on electrode properties.Howe...The computational simulation of the manufacturing process of lithium-ion battery composite electrodes based on mechanistic models allows capturing the influence of manufacturing parameters on electrode properties.However,ensuring that these properties match with experimental data is typically computationally expensive.In this work,we tackled this costly procedure by proposing a functional data-driven framework,aiming first to retrieve the early numerical values calculated from a molecular dynamics simulation to predict if the observable being calculated is prone to match with our range of experimental values,and in a second step,recover additional values of the ongoing simulation to predict its final result.We demonstrated this approach in the context of the calculation of electrode slurries viscosities.We report that for various electrode chemistries,the expected mechanistic simulation results can be obtained 11 times faster with respect to the complete simulations,while being accurate with a R^(2)_(score) equals to 0.96.展开更多
Electrode manufacturing process strongly impacts lithium-ion battery characteristics.The electrode slurry properties and the coating parameters are among the main factors influencing the electrode heterogeneity which ...Electrode manufacturing process strongly impacts lithium-ion battery characteristics.The electrode slurry properties and the coating parameters are among the main factors influencing the electrode heterogeneity which impacts the battery cell performance and lifetime.However,the analysis of the impact of electrode manufacturing parameters on the electrode heterogeneity is difficult to be quantified and automatized due to the large number of parameters that can be adjusted in the process.In this work,a data-driven methodology was developed for automatic assessment of the impact of parameters such as the formulation and liquid-to-solid ratio in the slurry,and the gap used for its coating on the current collector,on the electrodes heterogeneity.A dataset generated by experimental measurements was used for training and testing a Machine Learning(ML)classifier namely Gaussian Naives Bayes algorithm,for predicting if an electrode is homogeneous or heterogeneous depending on the manufacturing parameters.Lastly,through a 2D representation,the impact of the manufacturing parameters on the electrode heterogeneity was assessed in detail,paving the way towards a powerful tool for the optimization of next generation of battery electrodes.展开更多
基金The authors are grateful for the participation of the researchers in the workshop of NanOperando(GDR CNRS Nº2015)for the ground truth survey(2019/11,Energy Hub,Amiens,France)This research used resources of the Advanced Photon Source,a U.S.Department of Energy(DOE)Office of Science User Facility operated for the DOE Office of Science by Argonne National Laboratory under Contract No.DE-AC02-06CH11357.
文摘The segmentation of tomographic images of the battery electrode is a crucial processing step,which will have an additional impact on the results of material characterization and electrochemical simulation.However,manually labeling X-ray CT images(XCT)is time-consuming,and these XCT images are generally difficult to segment with histographical methods.We propose a deep learning approach with an asymmetrical depth encode-decoder convolutional neural network(CNN)for real-world battery material datasets.This network achieves high accuracy while requiring small amounts of labeled data and predicts a volume of billions voxel within few minutes.While applying supervised machine learning for segmenting real-world data,the ground truth is often absent.The results of segmentation are usually qualitatively justified by visual judgement.We try to unravel this fuzzy definition of segmentation quality by identifying the uncertainty due to the human bias diluted in the training data.Further CNN trainings using synthetic data show quantitative impact of such uncertainty on the determination of material’s properties.Nano-XCT datasets of various battery materials have been successfully segmented by training this neural network from scratch.We will also show that applying the transfer learning,which consists of reusing a well-trained network,can improve the accuracy of a similar dataset.
基金The authors acknowledge the European Union’s Horizon 2020 research and innovation program for the funding support through the European Research Council (grant agreement 772873,“ARTISTIC” project: ARTISTIC-ERC.M.D.and A.A.F.acknowledge the ALISTORE European Research Institute for funding support.A.A.F.acknowledges the Institut Universitaire de France for the support.A.A.F.and F.C.acknowledges the European Union’s Horizon 2020 research,and innovation program under grant agreement no.957189 (BIG MAP).
文摘The computational simulation of the manufacturing process of lithium-ion battery composite electrodes based on mechanistic models allows capturing the influence of manufacturing parameters on electrode properties.However,ensuring that these properties match with experimental data is typically computationally expensive.In this work,we tackled this costly procedure by proposing a functional data-driven framework,aiming first to retrieve the early numerical values calculated from a molecular dynamics simulation to predict if the observable being calculated is prone to match with our range of experimental values,and in a second step,recover additional values of the ongoing simulation to predict its final result.We demonstrated this approach in the context of the calculation of electrode slurries viscosities.We report that for various electrode chemistries,the expected mechanistic simulation results can be obtained 11 times faster with respect to the complete simulations,while being accurate with a R^(2)_(score) equals to 0.96.
基金A.A.F.and M.D.acknowledge the European Union’s Horizon 2020 research and innovation programme for the funding support through the European Research Council(grant agreement 772873,ARTISTIC proj-ect)M.D.,E.A.and A.A.F.acknowledge the ALISTORE European Research Institute for funding supportA.A.F.acknowledges the Institut Universitaire de France for the support.We acknowledge Dr.Fernando Caro,postdoctoral researcher at LRCS,for the proofreading of the article and useful comments.
文摘Electrode manufacturing process strongly impacts lithium-ion battery characteristics.The electrode slurry properties and the coating parameters are among the main factors influencing the electrode heterogeneity which impacts the battery cell performance and lifetime.However,the analysis of the impact of electrode manufacturing parameters on the electrode heterogeneity is difficult to be quantified and automatized due to the large number of parameters that can be adjusted in the process.In this work,a data-driven methodology was developed for automatic assessment of the impact of parameters such as the formulation and liquid-to-solid ratio in the slurry,and the gap used for its coating on the current collector,on the electrodes heterogeneity.A dataset generated by experimental measurements was used for training and testing a Machine Learning(ML)classifier namely Gaussian Naives Bayes algorithm,for predicting if an electrode is homogeneous or heterogeneous depending on the manufacturing parameters.Lastly,through a 2D representation,the impact of the manufacturing parameters on the electrode heterogeneity was assessed in detail,paving the way towards a powerful tool for the optimization of next generation of battery electrodes.
