Prediction on the relative permittivity of energy storage composite dielectrics using convolutional neural networks: A fast and accurate alternative to finite-element method
The relative permittivity is one of the essential parameters determines the physical polarization behaviors of the nanocomposite dielectrics in many applications, particularly for capacitive energy storage. Predicting the relative permittivity of particle/polymer nanocomposites from the microstructu...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2022-12-01
|
| Series: | iEnergy |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.23919/IEN.2022.0049 |
| _version_ | 1797952199127465984 |
|---|---|
| author | Shao-Long Zhong Di-Fan Liu Lei Huang Yong-Xin Zhang Qi Dong Zhi-Min Dang |
| author_facet | Shao-Long Zhong Di-Fan Liu Lei Huang Yong-Xin Zhang Qi Dong Zhi-Min Dang |
| author_sort | Shao-Long Zhong |
| collection | DOAJ |
| description | The relative permittivity is one of the essential parameters determines the physical polarization behaviors of the nanocomposite dielectrics in many applications, particularly for capacitive energy storage. Predicting the relative permittivity of particle/polymer nanocomposites from the microstructure is of great significance. However, the classical effective medium theory and physics-based numerical calculation represented by finite element method are time-consuming and cumbersome for complex structures and nonlinear problem. The work explores a novel architecture combining the convolutional neural network (ConvNet) and finite element method (FEM) to predict the relative permittivity of nanocomposite dielectrics with incorporated barium titanite (BT) particles in polyvinylidene fluoride (PVDF) matrix. The ConvNet was trained and evaluated on big datasets with 14266 training data and 3514 testing data generated form a programmatic algorithm. Through numerical experiments, we demonstrate that the trained network can efficiently provide an accurate agreement between the ConvNet model and FEM by virtue of the significant evaluation metrics R2, which reaches as high as 0.9783 and 0.9375 on training and testing data, respectively. The strong universality of the presented method allows for an extension to fast and accurately predict other properties of the nanocomposite dielectrics. |
| first_indexed | 2024-04-10T22:42:31Z |
| format | Article |
| id | doaj.art-3d9724d69687414f823f23b94d40653f |
| institution | Directory Open Access Journal |
| issn | 2771-9197 |
| language | English |
| last_indexed | 2024-04-10T22:42:31Z |
| publishDate | 2022-12-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | iEnergy |
| spelling | doaj.art-3d9724d69687414f823f23b94d40653f2023-01-16T03:28:12ZengTsinghua University PressiEnergy2771-91972022-12-011446347010.23919/IEN.2022.0049Prediction on the relative permittivity of energy storage composite dielectrics using convolutional neural networks: A fast and accurate alternative to finite-element methodShao-Long Zhong0Di-Fan Liu1Lei Huang2Yong-Xin Zhang3Qi Dong4Zhi-Min Dang5State Key Laboratory of Power System, Department of Electrical Engineering, Tsinghua University, Beijing 100084, ChinaState Key Laboratory of Power System, Department of Electrical Engineering, Tsinghua University, Beijing 100084, ChinaState Key Laboratory of Power System, Department of Electrical Engineering, Tsinghua University, Beijing 100084, ChinaState Key Laboratory of Power System, Department of Electrical Engineering, Tsinghua University, Beijing 100084, ChinaState Key Laboratory of Power System, Department of Electrical Engineering, Tsinghua University, Beijing 100084, ChinaState Key Laboratory of Power System, Department of Electrical Engineering, Tsinghua University, Beijing 100084, ChinaThe relative permittivity is one of the essential parameters determines the physical polarization behaviors of the nanocomposite dielectrics in many applications, particularly for capacitive energy storage. Predicting the relative permittivity of particle/polymer nanocomposites from the microstructure is of great significance. However, the classical effective medium theory and physics-based numerical calculation represented by finite element method are time-consuming and cumbersome for complex structures and nonlinear problem. The work explores a novel architecture combining the convolutional neural network (ConvNet) and finite element method (FEM) to predict the relative permittivity of nanocomposite dielectrics with incorporated barium titanite (BT) particles in polyvinylidene fluoride (PVDF) matrix. The ConvNet was trained and evaluated on big datasets with 14266 training data and 3514 testing data generated form a programmatic algorithm. Through numerical experiments, we demonstrate that the trained network can efficiently provide an accurate agreement between the ConvNet model and FEM by virtue of the significant evaluation metrics R2, which reaches as high as 0.9783 and 0.9375 on training and testing data, respectively. The strong universality of the presented method allows for an extension to fast and accurately predict other properties of the nanocomposite dielectrics.https://www.sciopen.com/article/10.23919/IEN.2022.0049relative permittivitynanocomposite dielectricsconvolutional neural networksfinite element methodprediction accuracy |
| spellingShingle | Shao-Long Zhong Di-Fan Liu Lei Huang Yong-Xin Zhang Qi Dong Zhi-Min Dang Prediction on the relative permittivity of energy storage composite dielectrics using convolutional neural networks: A fast and accurate alternative to finite-element method iEnergy relative permittivity nanocomposite dielectrics convolutional neural networks finite element method prediction accuracy |
| title | Prediction on the relative permittivity of energy storage composite dielectrics using convolutional neural networks: A fast and accurate alternative to finite-element method |
| title_full | Prediction on the relative permittivity of energy storage composite dielectrics using convolutional neural networks: A fast and accurate alternative to finite-element method |
| title_fullStr | Prediction on the relative permittivity of energy storage composite dielectrics using convolutional neural networks: A fast and accurate alternative to finite-element method |
| title_full_unstemmed | Prediction on the relative permittivity of energy storage composite dielectrics using convolutional neural networks: A fast and accurate alternative to finite-element method |
| title_short | Prediction on the relative permittivity of energy storage composite dielectrics using convolutional neural networks: A fast and accurate alternative to finite-element method |
| title_sort | prediction on the relative permittivity of energy storage composite dielectrics using convolutional neural networks a fast and accurate alternative to finite element method |
| topic | relative permittivity nanocomposite dielectrics convolutional neural networks finite element method prediction accuracy |
| url | https://www.sciopen.com/article/10.23919/IEN.2022.0049 |
| work_keys_str_mv | AT shaolongzhong predictionontherelativepermittivityofenergystoragecompositedielectricsusingconvolutionalneuralnetworksafastandaccuratealternativetofiniteelementmethod AT difanliu predictionontherelativepermittivityofenergystoragecompositedielectricsusingconvolutionalneuralnetworksafastandaccuratealternativetofiniteelementmethod AT leihuang predictionontherelativepermittivityofenergystoragecompositedielectricsusingconvolutionalneuralnetworksafastandaccuratealternativetofiniteelementmethod AT yongxinzhang predictionontherelativepermittivityofenergystoragecompositedielectricsusingconvolutionalneuralnetworksafastandaccuratealternativetofiniteelementmethod AT qidong predictionontherelativepermittivityofenergystoragecompositedielectricsusingconvolutionalneuralnetworksafastandaccuratealternativetofiniteelementmethod AT zhimindang predictionontherelativepermittivityofenergystoragecompositedielectricsusingconvolutionalneuralnetworksafastandaccuratealternativetofiniteelementmethod |