Diagnosing health in composite battery electrodes with explainable deep learning and partial charging data
Lithium-ion batteries with composite anodes of graphite and silicon are increasingly being used. However, their degradation pathways are complicated due to the blended nature of the electrodes, with graphite and silicon degrading at different rates. Here, we develop a deep learning health diagnostic...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-05-01
|
| Series: | Energy and AI |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666546824000181 |
| _version_ | 1797267642487144448 |
|---|---|
| author | Haijun Ruan Niall Kirkaldy Gregory J. Offer Billy Wu |
| author_facet | Haijun Ruan Niall Kirkaldy Gregory J. Offer Billy Wu |
| author_sort | Haijun Ruan |
| collection | DOAJ |
| description | Lithium-ion batteries with composite anodes of graphite and silicon are increasingly being used. However, their degradation pathways are complicated due to the blended nature of the electrodes, with graphite and silicon degrading at different rates. Here, we develop a deep learning health diagnostic framework to rapidly quantify and separate the different degradation rates of graphite and silicon in composite anodes using partial charging data. The convolutional neural network (CNN), trained with synthetic data, uses experimental partial charging data to diagnose electrode-level health of tested batteries, with errors of less than 3.1% (corresponding to the loss of active material reaching ∼75%). Sensitivity analysis of the capacity-voltage curve under different degradation modes is performed to provide a physically informed voltage window for diagnostics with partial charging data. By using the gradient-weighted class activation mapping approach, we provide explainable insights into how these CNNs work; highlighting regions of the voltage-curve to which they are most sensitive. Robustness is validated by introducing noise to the data, with no significant negative impact on the diagnostic accuracy for noise levels below 10 mV, thus highlighting the potential for deep learning approaches in the diagnostics of lithium-ion battery performance under real-world conditions. The framework presented here can be generalised to other cell formats and chemistries, providing robust and explainable battery diagnostics for both conventional single material electrodes, but also the more challenging composite electrodes. |
| first_indexed | 2024-04-25T01:19:50Z |
| format | Article |
| id | doaj.art-f6b56a7f81db4c1e8fe8f7c063721b76 |
| institution | Directory Open Access Journal |
| issn | 2666-5468 |
| language | English |
| last_indexed | 2024-04-25T01:19:50Z |
| publishDate | 2024-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy and AI |
| spelling | doaj.art-f6b56a7f81db4c1e8fe8f7c063721b762024-03-09T09:29:35ZengElsevierEnergy and AI2666-54682024-05-0116100352Diagnosing health in composite battery electrodes with explainable deep learning and partial charging dataHaijun Ruan0Niall Kirkaldy1Gregory J. Offer2Billy Wu3Dyson School of Design Engineering, Imperial College London, SW7 2AZ, London, UK; Centre for E-Mobility and Clean Growth Research, Coventry University, Coventry, CV1 5FB, UK; Corresponding authors at: Dyson School of Design Engineering, Imperial College London, SW7 2AZ, London, UK.Department of Mechanical Engineering, Imperial College London, SW7 2AZ, London, UK; The Faraday Institution, Harwell Science and Innovation Campus, OX11 0RA, Didcot, UKDepartment of Mechanical Engineering, Imperial College London, SW7 2AZ, London, UK; The Faraday Institution, Harwell Science and Innovation Campus, OX11 0RA, Didcot, UKDyson School of Design Engineering, Imperial College London, SW7 2AZ, London, UK; The Faraday Institution, Harwell Science and Innovation Campus, OX11 0RA, Didcot, UK; Corresponding authors at: Dyson School of Design Engineering, Imperial College London, SW7 2AZ, London, UK.Lithium-ion batteries with composite anodes of graphite and silicon are increasingly being used. However, their degradation pathways are complicated due to the blended nature of the electrodes, with graphite and silicon degrading at different rates. Here, we develop a deep learning health diagnostic framework to rapidly quantify and separate the different degradation rates of graphite and silicon in composite anodes using partial charging data. The convolutional neural network (CNN), trained with synthetic data, uses experimental partial charging data to diagnose electrode-level health of tested batteries, with errors of less than 3.1% (corresponding to the loss of active material reaching ∼75%). Sensitivity analysis of the capacity-voltage curve under different degradation modes is performed to provide a physically informed voltage window for diagnostics with partial charging data. By using the gradient-weighted class activation mapping approach, we provide explainable insights into how these CNNs work; highlighting regions of the voltage-curve to which they are most sensitive. Robustness is validated by introducing noise to the data, with no significant negative impact on the diagnostic accuracy for noise levels below 10 mV, thus highlighting the potential for deep learning approaches in the diagnostics of lithium-ion battery performance under real-world conditions. The framework presented here can be generalised to other cell formats and chemistries, providing robust and explainable battery diagnostics for both conventional single material electrodes, but also the more challenging composite electrodes.http://www.sciencedirect.com/science/article/pii/S2666546824000181Lithium-ion batteryComposite electrodeSiliconDegradation diagnosticExplainable deep learningPartial charging |
| spellingShingle | Haijun Ruan Niall Kirkaldy Gregory J. Offer Billy Wu Diagnosing health in composite battery electrodes with explainable deep learning and partial charging data Energy and AI Lithium-ion battery Composite electrode Silicon Degradation diagnostic Explainable deep learning Partial charging |
| title | Diagnosing health in composite battery electrodes with explainable deep learning and partial charging data |
| title_full | Diagnosing health in composite battery electrodes with explainable deep learning and partial charging data |
| title_fullStr | Diagnosing health in composite battery electrodes with explainable deep learning and partial charging data |
| title_full_unstemmed | Diagnosing health in composite battery electrodes with explainable deep learning and partial charging data |
| title_short | Diagnosing health in composite battery electrodes with explainable deep learning and partial charging data |
| title_sort | diagnosing health in composite battery electrodes with explainable deep learning and partial charging data |
| topic | Lithium-ion battery Composite electrode Silicon Degradation diagnostic Explainable deep learning Partial charging |
| url | http://www.sciencedirect.com/science/article/pii/S2666546824000181 |
| work_keys_str_mv | AT haijunruan diagnosinghealthincompositebatteryelectrodeswithexplainabledeeplearningandpartialchargingdata AT niallkirkaldy diagnosinghealthincompositebatteryelectrodeswithexplainabledeeplearningandpartialchargingdata AT gregoryjoffer diagnosinghealthincompositebatteryelectrodeswithexplainabledeeplearningandpartialchargingdata AT billywu diagnosinghealthincompositebatteryelectrodeswithexplainabledeeplearningandpartialchargingdata |