A Novel Online State of Health Estimation Method for Electric Vehicle Pouch Cells Using Magnetic Field Imaging and Convolution Neural Networks
Lithium-ion batteries (LiBs) are used as the main power source in electric vehicles (EVs). Despite their high energy density and commercial availability, LiBs chronically suffer from non-uniform cell ageing, leading to early capacity fade in the battery packs. In this paper, a non-invasive, online c...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Electrochem |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-3293/3/4/51 |
| _version_ | 1797460220785459200 |
|---|---|
| author | Mehrnaz Javadipour Toshan Wickramanayake Seyed Amir Alavi Kamyar Mehran |
| author_facet | Mehrnaz Javadipour Toshan Wickramanayake Seyed Amir Alavi Kamyar Mehran |
| author_sort | Mehrnaz Javadipour |
| collection | DOAJ |
| description | Lithium-ion batteries (LiBs) are used as the main power source in electric vehicles (EVs). Despite their high energy density and commercial availability, LiBs chronically suffer from non-uniform cell ageing, leading to early capacity fade in the battery packs. In this paper, a non-invasive, online characterisation method based on deep learning models is proposed for cell-level SoH estimation. For an accurate measurement of the state of health (SoH), we need to characterize electrochemical capacity fade scenarios carefully. Then, with the help of real-time monitoring, the control systems can reduce the LiB’s degradation. The proposed method, which is based on convolutional neural networks (CNN), characterises the changes in current density distributions originating from the positive electrodes in different SoH states. For training and classification by the deep learning model, current density images (CDIs) were experimentally acquired in different ageing conditions. The results confirm the efficiency of the proposed approach in online SoH estimation and the prediction of the capacity fade scenarios. |
| first_indexed | 2024-03-09T17:02:04Z |
| format | Article |
| id | doaj.art-e93bb1a1c49e4ae8ac18d2c59795fd66 |
| institution | Directory Open Access Journal |
| issn | 2673-3293 |
| language | English |
| last_indexed | 2024-03-09T17:02:04Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electrochem |
| spelling | doaj.art-e93bb1a1c49e4ae8ac18d2c59795fd662023-11-24T14:29:21ZengMDPI AGElectrochem2673-32932022-11-013476978810.3390/electrochem3040051A Novel Online State of Health Estimation Method for Electric Vehicle Pouch Cells Using Magnetic Field Imaging and Convolution Neural NetworksMehrnaz Javadipour0Toshan Wickramanayake1Seyed Amir Alavi2Kamyar Mehran3School of Electronic Engineering and Computer Science, Queen Mary University of London, Mile End Road, London E1 4NS, UKSchool of Electronic Engineering and Computer Science, Queen Mary University of London, Mile End Road, London E1 4NS, UKSchool of Electronic Engineering and Computer Science, Queen Mary University of London, Mile End Road, London E1 4NS, UKSchool of Electronic Engineering and Computer Science, Queen Mary University of London, Mile End Road, London E1 4NS, UKLithium-ion batteries (LiBs) are used as the main power source in electric vehicles (EVs). Despite their high energy density and commercial availability, LiBs chronically suffer from non-uniform cell ageing, leading to early capacity fade in the battery packs. In this paper, a non-invasive, online characterisation method based on deep learning models is proposed for cell-level SoH estimation. For an accurate measurement of the state of health (SoH), we need to characterize electrochemical capacity fade scenarios carefully. Then, with the help of real-time monitoring, the control systems can reduce the LiB’s degradation. The proposed method, which is based on convolutional neural networks (CNN), characterises the changes in current density distributions originating from the positive electrodes in different SoH states. For training and classification by the deep learning model, current density images (CDIs) were experimentally acquired in different ageing conditions. The results confirm the efficiency of the proposed approach in online SoH estimation and the prediction of the capacity fade scenarios.https://www.mdpi.com/2673-3293/3/4/51condition monitoringstate of healthconvolutional neural networkcurrent density distributionelectric vehicleslithium-ion batteries |
| spellingShingle | Mehrnaz Javadipour Toshan Wickramanayake Seyed Amir Alavi Kamyar Mehran A Novel Online State of Health Estimation Method for Electric Vehicle Pouch Cells Using Magnetic Field Imaging and Convolution Neural Networks Electrochem condition monitoring state of health convolutional neural network current density distribution electric vehicles lithium-ion batteries |
| title | A Novel Online State of Health Estimation Method for Electric Vehicle Pouch Cells Using Magnetic Field Imaging and Convolution Neural Networks |
| title_full | A Novel Online State of Health Estimation Method for Electric Vehicle Pouch Cells Using Magnetic Field Imaging and Convolution Neural Networks |
| title_fullStr | A Novel Online State of Health Estimation Method for Electric Vehicle Pouch Cells Using Magnetic Field Imaging and Convolution Neural Networks |
| title_full_unstemmed | A Novel Online State of Health Estimation Method for Electric Vehicle Pouch Cells Using Magnetic Field Imaging and Convolution Neural Networks |
| title_short | A Novel Online State of Health Estimation Method for Electric Vehicle Pouch Cells Using Magnetic Field Imaging and Convolution Neural Networks |
| title_sort | novel online state of health estimation method for electric vehicle pouch cells using magnetic field imaging and convolution neural networks |
| topic | condition monitoring state of health convolutional neural network current density distribution electric vehicles lithium-ion batteries |
| url | https://www.mdpi.com/2673-3293/3/4/51 |
| work_keys_str_mv | AT mehrnazjavadipour anovelonlinestateofhealthestimationmethodforelectricvehiclepouchcellsusingmagneticfieldimagingandconvolutionneuralnetworks AT toshanwickramanayake anovelonlinestateofhealthestimationmethodforelectricvehiclepouchcellsusingmagneticfieldimagingandconvolutionneuralnetworks AT seyedamiralavi anovelonlinestateofhealthestimationmethodforelectricvehiclepouchcellsusingmagneticfieldimagingandconvolutionneuralnetworks AT kamyarmehran anovelonlinestateofhealthestimationmethodforelectricvehiclepouchcellsusingmagneticfieldimagingandconvolutionneuralnetworks AT mehrnazjavadipour novelonlinestateofhealthestimationmethodforelectricvehiclepouchcellsusingmagneticfieldimagingandconvolutionneuralnetworks AT toshanwickramanayake novelonlinestateofhealthestimationmethodforelectricvehiclepouchcellsusingmagneticfieldimagingandconvolutionneuralnetworks AT seyedamiralavi novelonlinestateofhealthestimationmethodforelectricvehiclepouchcellsusingmagneticfieldimagingandconvolutionneuralnetworks AT kamyarmehran novelonlinestateofhealthestimationmethodforelectricvehiclepouchcellsusingmagneticfieldimagingandconvolutionneuralnetworks |