Basab Ranjan Das Goswami
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Basab Ranjan Das Goswami has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Vitaliy Yurkiv
University of Arizona
9 shared publications Farzad Mashayek
University of Arizona
6 shared publicationsMarco Ragone
5 shared publications- Massimiliano Mastrogiorgio
University of Illinois at Chicago
5 shared publications - Todd A. Kingston
Iowa State University
3 shared publications Yasaman AbdiSobbouhi
University of Arizona
3 shared publications
Latest Publications
- Open Access
- 27 August 2026
- Published by Elsevier in SSRN Electronic Journal
Temperature and Voltage Effects on the Impedance Response of 4680 Lithium-Ion Batteries: Experimental Analysis and Parametric Sensitivity
This study investigates the effects of temperature and cell voltage on the electrochemical and thermal behavior of commercial 24 Ah 4680-format graphite/LiNi0.8Mn0.1Co0.1O2 (NMC811) lithium-ion batteries (LIBs). We present electrochemical impedance spectroscopy (EIS) measured at four temperatures (-14 °C, 2 °C, 23 °C, 42 °C) and multiple cell voltages, and analyze the results using the Distribution of relaxation times (DRT). Nyquist and Bode plots reveal strong temperature- and voltage-dependent behavior in ohmic, charge-transfer, and diffusion resistances, but overlapping processes obscure definitive attribution. DRT provides time-resolved separation, identifying contributions from anode/cathode charge transfer (CT), anode solid electrolyte interphase (SEI), lithium plating, cathode electrolyte interface, and solid-state diffusion. With increasing temperature, the mid-frequency arc contracts by ~5–10, and time constants shift by 102–103 toward higher frequencies. The nominal-voltage condition exhibits the minimum resistance, while the full-charge and low-voltage conditions show larger CT and diffusion contributions. At -14 °C, a plating-related peak appears at high voltages, while at 42 °C, the spectrum simplifies to CT and diffusion. A sensitivity analysis of the regularization parameter shows an approximately 5% DRT change for a 10% decrease in λ at -14 °C and less than 1% at the warmer conditions. The results establish an experimental impedance and DRT benchmark for commercial 4680 cells and identify the operating conditions under which cold-temperature interfacial and transport limitations become dominant.
- 27 August 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessTemperature and Voltage Effects on the Impedance Response of 4680 Lithium-Ion Batteries: Experimental Analysis and Parametric Sensitivity
This study investigates the effects of temperature and cell voltage on the electrochemical and thermal behavior of commercial 24 Ah 4680-format graphite/LiNi0.8Mn0.1Co0.1O2 (NMC811) lithium-ion batteries (LIBs). We present electrochemical impedance spectroscopy (EIS) measured at four temperatures (-14 °C, 2 °C, 23 °C, 42 °C) and multiple cell voltages, and analyze the results using the Distribution of relaxation times (DRT). Nyquist and Bode plots reveal strong temperature- and voltage-dependent behavior in ohmic, charge-transfer, and diffusion resistances, but overlapping processes obscure definitive attribution. DRT provides time-resolved separation, identifying contributions from anode/cathode charge transfer (CT), anode solid electrolyte interphase (SEI), lithium plating, cathode electrolyte interface, and solid-state diffusion. With increasing temperature, the mid-frequency arc contracts by ~5–10, and time constants shift by 102–103 toward higher frequencies. The nominal-voltage condition exhibits the minimum resistance, while the full-charge and low-voltage conditions show larger CT and diffusion contributions. At -14 °C, a plating-related peak appears at high voltages, while at 42 °C, the spectrum simplifies to CT and diffusion. A sensitivity analysis of the regularization parameter shows an approximately 5% DRT change for a 10% decrease in λ at -14 °C and less than 1% at the warmer conditions. The results establish an experimental impedance and DRT benchmark for commercial 4680 cells and identify the operating conditions under which cold-temperature interfacial and transport limitations become dominant.
- 11 July 2025
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2025-01 (8) , 817
Multiphysics Modeling of Commercial Batteries for Predicting Thermal Behavior Under Variable Environmental and Operational Conditions
Understanding the thermal and electrochemical responses of lithium-ion batteries (LIBs), especially under high-stress scenarios, is vital for advancing battery safety and reliability. In this study, we extend our previously developed multiphysics model1 to simulate the thermal behavior of high capacity (e.g., 24 Ah) commercial cylindrical batteries. This model integrates electrochemical, thermal, and degradation phenomena to predict conditions that could lead to thermal runaway (TR) under various C-rates, temperatures, and humidity levels. Experimental tests were conducted to inform model parameters, involving cycling at different constant C-rates and under simulated driving cycles like the FTP75. The environmental conditions varied from –20°C to 40°C across multiple humidity levels to replicate real-world operating conditions. Electrochemical impedance spectroscopy (EIS) measurements were taken at various states of discharge and after prolonged cycling to monitor battery degradation. These data, alongside temperature and heat generation measurements, informed the multiphysics model implemented in COMSOL. The model leverages a pseudo-2D (P2D) electrochemical framework coupled with a 3D thermal model to simulate heat generation, SEI formation, and degradation kinetics. This integrated approach allows the simulation of both short-term thermal spikes during high C-rate discharge and gradual temperature increases from SEI decomposition. By calibrating with real experimental data, this model can effectively forecast temperature evolution under different stress conditions, providing insights into TR risks in practical applications. This work underscores the potential of advanced modeling techniques in improving battery management systems and safety protocols for large-format cylindrical cells. Acknowledgment: Authors gratefully acknowledge financial support from the Department of Defense (DoD) Office of Naval Research (ONR) and Air Force Office of Scientific Research through the Defense Established Program to Stimulate Competitive Research (DEPSCoR) under award number FA9550-24-1-0164. Reference (1) Das Goswami, B. R.; Abdisobbouhi, Y.; Du, H.; Mashayek, F.; Kingston, T. A.; Yurkiv, V. Advancing Battery Safety: Integrating Multiphysics and Machine Learning for Thermal Runaway Prediction in Lithium-Ion Battery Module. J Power Sources 2024, 614. https://doi.org/10.1016/j.jpowsour.2024.235015.
- 11 July 2025
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2025-01 (8) , 817
Multiphysics Modeling of Commercial Batteries for Predicting Thermal Behavior Under Variable Environmental and Operational Conditions
Understanding the thermal and electrochemical responses of lithium-ion batteries (LIBs), especially under high-stress scenarios, is vital for advancing battery safety and reliability. In this study, we extend our previously developed multiphysics model1 to simulate the thermal behavior of high capacity (e.g., 24 Ah) commercial cylindrical batteries. This model integrates electrochemical, thermal, and degradation phenomena to predict conditions that could lead to thermal runaway (TR) under various C-rates, temperatures, and humidity levels. Experimental tests were conducted to inform model parameters, involving cycling at different constant C-rates and under simulated driving cycles like the FTP75. The environmental conditions varied from –20°C to 40°C across multiple humidity levels to replicate real-world operating conditions. Electrochemical impedance spectroscopy (EIS) measurements were taken at various states of discharge and after prolonged cycling to monitor battery degradation. These data, alongside temperature and heat generation measurements, informed the multiphysics model implemented in COMSOL. The model leverages a pseudo-2D (P2D) electrochemical framework coupled with a 3D thermal model to simulate heat generation, SEI formation, and degradation kinetics. This integrated approach allows the simulation of both short-term thermal spikes during high C-rate discharge and gradual temperature increases from SEI decomposition. By calibrating with real experimental data, this model can effectively forecast temperature evolution under different stress conditions, providing insights into TR risks in practical applications. This work underscores the potential of advanced modeling techniques in improving battery management systems and safety protocols for large-format cylindrical cells. Acknowledgment: Authors gratefully acknowledge financial support from the Department of Defense (DoD) Office of Naval Research (ONR) and Air Force Office of Scientific Research through the Defense Established Program to Stimulate Competitive Research (DEPSCoR) under award number FA9550-24-1-0164. Reference (1) Das Goswami, B. R.; Abdisobbouhi, Y.; Du, H.; Mashayek, F.; Kingston, T. A.; Yurkiv, V. Advancing Battery Safety: Integrating Multiphysics and Machine Learning for Thermal Runaway Prediction in Lithium-Ion Battery Module. J Power Sources 2024, 614. https://doi.org/10.1016/j.jpowsour.2024.235015.
- 22 November 2024
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2024-02 (3) , 380
From Electrochemical Analysis to Machine Learning Prediction: A Comprehensive Approach to LIB Safety
The advancement of lithium-ion battery (LIB) technology has been pivotal in powering a wide range of applications, from portable electronics to electric vehicles (EVs). However, the safety of LIBs remains a significant concern, primarily due to the risk of thermal runaway (TR), a process where an increase in temperature leads to a self-sustaining chain reaction resulting in catastrophic failure. Our study introduces a groundbreaking framework that integrates multiphysics modeling with machine learning (ML) to predict the onset of TR in LIB modules, thereby advancing battery safety and reliability. The multiphysics model developed in this research incorporates the comprehensive electrochemical and thermal behavior of LIBs, with a particular focus on the degradation mechanisms that lead to TR. This includes a detailed analysis of the breakdown of solid electrolyte interface (SEI) and its impact on battery stability. The model simulates various operational scenarios, such as constant charge/discharge and dynamic driving cycles, to replicate real-world battery usage. The thermal, electrochemical, and mechanical stresses are computed, enabling the identification of conditions that cause TR. In parallel, we have implemented an ML framework utilizing a hybrid Graph Neural Network-Long Short-Term Memory (GNN-LSTM) algorithm. This innovative approach leverages the spatio-temporal data generated from the multiphysics simulations, effectively predicting temperature evolution across the battery module. The GNN component captures spatial dependencies related to the battery's internal structure and thermal pathways, while the LSTM network models the temporal dynamics of the battery's thermal response. This dual mechanism ensures a comprehensive analysis of the potential hotspots and thermal anomalies that precede TR events. The model's accuracy in representing the physical phenomena was validated against experimental discharge data at various C-rates, showing a high correlation with real-world battery behavior. One key finding was the identification of temperature thresholds where SEI decomposition accelerates, leading to rapid temperature increases. The model also highlighted the impact of operational stress, such as high C-rates, on accelerating degradation and advancing the onset of TR. Our findings reveal that the integrated multiphysics-ML model can accurately forecast critical thermal events in LIBs, offering a substantial lead time before the onset of TR. This predictive capability enables proactive measures to be taken, such as system shutdown or cooling interventions, thus averting potential damage and enhancing battery safety. Moreover, the model's adaptability to various battery configurations and operational conditions signifies a significant leap toward battery safety solutions. VY and TAK gratefully acknowledge financial support from the Department of Defense (DoD) Office of Naval Research (ONR) through the Defense Established Program to Stimulate Competitive Research (DEPSCoR).
- 22 November 2024
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2024-02 (3) , 380
From Electrochemical Analysis to Machine Learning Prediction: A Comprehensive Approach to LIB Safety
The advancement of lithium-ion battery (LIB) technology has been pivotal in powering a wide range of applications, from portable electronics to electric vehicles (EVs). However, the safety of LIBs remains a significant concern, primarily due to the risk of thermal runaway (TR), a process where an increase in temperature leads to a self-sustaining chain reaction resulting in catastrophic failure. Our study introduces a groundbreaking framework that integrates multiphysics modeling with machine learning (ML) to predict the onset of TR in LIB modules, thereby advancing battery safety and reliability. The multiphysics model developed in this research incorporates the comprehensive electrochemical and thermal behavior of LIBs, with a particular focus on the degradation mechanisms that lead to TR. This includes a detailed analysis of the breakdown of solid electrolyte interface (SEI) and its impact on battery stability. The model simulates various operational scenarios, such as constant charge/discharge and dynamic driving cycles, to replicate real-world battery usage. The thermal, electrochemical, and mechanical stresses are computed, enabling the identification of conditions that cause TR. In parallel, we have implemented an ML framework utilizing a hybrid Graph Neural Network-Long Short-Term Memory (GNN-LSTM) algorithm. This innovative approach leverages the spatio-temporal data generated from the multiphysics simulations, effectively predicting temperature evolution across the battery module. The GNN component captures spatial dependencies related to the battery's internal structure and thermal pathways, while the LSTM network models the temporal dynamics of the battery's thermal response. This dual mechanism ensures a comprehensive analysis of the potential hotspots and thermal anomalies that precede TR events. The model's accuracy in representing the physical phenomena was validated against experimental discharge data at various C-rates, showing a high correlation with real-world battery behavior. One key finding was the identification of temperature thresholds where SEI decomposition accelerates, leading to rapid temperature increases. The model also highlighted the impact of operational stress, such as high C-rates, on accelerating degradation and advancing the onset of TR. Our findings reveal that the integrated multiphysics-ML model can accurately forecast critical thermal events in LIBs, offering a substantial lead time before the onset of TR. This predictive capability enables proactive measures to be taken, such as system shutdown or cooling interventions, thus averting potential damage and enhancing battery safety. Moreover, the model's adaptability to various battery configurations and operational conditions signifies a significant leap toward battery safety solutions. VY and TAK gratefully acknowledge financial support from the Department of Defense (DoD) Office of Naval Research (ONR) through the Defense Established Program to Stimulate Competitive Research (DEPSCoR).
- 9 August 2024
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2024-01 (2) , 324
Advancements in Li-Ion Battery Safety: A Multiphysics and Deep Learning Approach for Thermal Runaway Prediction
The increasing adoption of Lithium-ion batteries (LIBs) in various applications necessitates an enhanced focus on safety, particularly concerning the thermal runaway (TR) phenomenon. This study introduces a novel framework combining multiphysics modeling and deep learning (DL) to predict TR in cylindrical Li-ion batteries. The primary objective is to prevent catastrophic battery failures by identifying critical thermal conditions leading to TR. Our methodology integrates state-of-the-art convolutional neural networks (CNNs) and the "You Only Look Once" (YOLO) object detection model to classify and detect the evolution of TR stages in LIBs. The CNNs, trained on simulated thermal images generated through comprehensive multiphysics modeling, classify TR into three distinct stages: safe operation, critical condition, and actual TR occurrence. The YOLO model further pinpoints the location of TR heat sources, enhancing the predictive accuracy. The multiphysics model employed captures the coupled thermal and electrochemical behavior of LIBs, focusing on the solid electrolyte interface (SEI) formation/decomposition on the anode as the primary degradation mechanism. The simulated thermal imagery, reflecting real-time battery conditions, serves as a dataset for training our DL models. This combination of physics-based and data-driven approaches allows for a detailed understanding of TR dynamics. In our study, we also explored the efficiency of other neural network architectures, notably ResNet, EfficientNet, and MobileNet for their potential in TR prediction. ResNet, known for its deep residual learning framework, demonstrated proficiency in handling the complex, layered features of thermal images. EfficientNet, optimized for efficiency and accuracy, showed promise in its scalable architecture and balanced depth, width, and resolution, making it a viable alternative for real-time TR detection. The MobileNet known for its lightweight architecture and efficiency on mobile devices, was evaluated for its capability to process thermal images in a resource-constrained environment. It demonstrated a remarkable balance between computational efficiency and predictive accuracy, making it a viable option for real-time TR monitoring in portable LIB applications. While MobileNet, ResNet, and EfficientNet each showed potential in their respective capacities, our primary CNN-YOLO framework emerged as the most effective for TR prediction in this study. Its proficiency in extracting spatial features and detecting anomalies in real-time was critical for early TR identification in LIBs. Results demonstrate high accuracy in predicting TR stages and heat source locations, emphasizing the ability of the integrated approach. The study highlights the importance of thermal management and real-time monitoring in LIBs, offering insights into the thermal behavior under various load conditions. The predictive framework not only advances the fundamental understanding of TR in LIBs but also provides practical implications for enhancing battery safety in applications like electric vehicles and consumer electronics. In conclusion, this work presents a significant stride in battery research, paving the way for safer and more reliable energy storage solutions. The combined multiphysics modeling and DL framework offer a robust tool for predicting and preventing TR in LIBs, contributing to the broader goal of advancing battery technology in the modern energy landscape.
- 9 August 2024
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2024-01 (2) , 324
Advancements in Li-Ion Battery Safety: A Multiphysics and Deep Learning Approach for Thermal Runaway Prediction
The increasing adoption of Lithium-ion batteries (LIBs) in various applications necessitates an enhanced focus on safety, particularly concerning the thermal runaway (TR) phenomenon. This study introduces a novel framework combining multiphysics modeling and deep learning (DL) to predict TR in cylindrical Li-ion batteries. The primary objective is to prevent catastrophic battery failures by identifying critical thermal conditions leading to TR. Our methodology integrates state-of-the-art convolutional neural networks (CNNs) and the "You Only Look Once" (YOLO) object detection model to classify and detect the evolution of TR stages in LIBs. The CNNs, trained on simulated thermal images generated through comprehensive multiphysics modeling, classify TR into three distinct stages: safe operation, critical condition, and actual TR occurrence. The YOLO model further pinpoints the location of TR heat sources, enhancing the predictive accuracy. The multiphysics model employed captures the coupled thermal and electrochemical behavior of LIBs, focusing on the solid electrolyte interface (SEI) formation/decomposition on the anode as the primary degradation mechanism. The simulated thermal imagery, reflecting real-time battery conditions, serves as a dataset for training our DL models. This combination of physics-based and data-driven approaches allows for a detailed understanding of TR dynamics. In our study, we also explored the efficiency of other neural network architectures, notably ResNet, EfficientNet, and MobileNet for their potential in TR prediction. ResNet, known for its deep residual learning framework, demonstrated proficiency in handling the complex, layered features of thermal images. EfficientNet, optimized for efficiency and accuracy, showed promise in its scalable architecture and balanced depth, width, and resolution, making it a viable alternative for real-time TR detection. The MobileNet known for its lightweight architecture and efficiency on mobile devices, was evaluated for its capability to process thermal images in a resource-constrained environment. It demonstrated a remarkable balance between computational efficiency and predictive accuracy, making it a viable option for real-time TR monitoring in portable LIB applications. While MobileNet, ResNet, and EfficientNet each showed potential in their respective capacities, our primary CNN-YOLO framework emerged as the most effective for TR prediction in this study. Its proficiency in extracting spatial features and detecting anomalies in real-time was critical for early TR identification in LIBs. Results demonstrate high accuracy in predicting TR stages and heat source locations, emphasizing the ability of the integrated approach. The study highlights the importance of thermal management and real-time monitoring in LIBs, offering insights into the thermal behavior under various load conditions. The predictive framework not only advances the fundamental understanding of TR in LIBs but also provides practical implications for enhancing battery safety in applications like electric vehicles and consumer electronics. In conclusion, this work presents a significant stride in battery research, paving the way for safer and more reliable energy storage solutions. The combined multiphysics modeling and DL framework offer a robust tool for predicting and preventing TR in LIBs, contributing to the broader goal of advancing battery technology in the modern energy landscape.
- 19 January 2024
- Published by Elsevier in Journal of Power Sources
- Vol. 595
A combined multiphysics modeling and deep learning framework to predict thermal runaway in cylindrical Li-ion batteries
- 19 January 2024
- Published by Elsevier in Journal of Power Sources
- Vol. 595
A combined multiphysics modeling and deep learning framework to predict thermal runaway in cylindrical Li-ion batteries
- 9 October 2022
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2022-02 (3) , 230
Predicting Thermal Failures Using an Advanced Data-Driven Modeling Framework in a Cylindrical Li-Ion Battery Pack
Li-ion cells have been widely used in battery electric vehicles (BEV), hybrid electric vehicles (HEV), plug-in hybrid electric vehicles (PHEV), and stationary energy storage units due to their high specific energy and excellent cycle life. However, the safety of Li-ion battery (LIB) packs has become a vital issue, especially under extreme or abusive conditions. Fire and explosion due to the onset of thermal runaway often lead to catastrophic damages. Thermal failures are caused by drastic and successive processes and reactions that feed into one another, eventually leading to fire and explosion. Thus, one of the most crucial current research goals is to steer LIBs’ technology toward long-lasting and safe operation. In this work, we employ data-driven methods to predict and potentially prevent the thermal runaway (TRA) in a LIB battery pack with various cooling systems. Specifically, we use several deep learning (DL) techniques to learn and predict the likelihood of the TRA, using thermal images acquired from the multi-physics modeling of LIBs. The multi-physics modeling approach comprises a coupled thermal, electrochemical (P2D) model1 and degradation due to the solid electrolyte interface (SEI) formation/decomposition sub-models.2 The geometrical and material properties of the battery pack are taken from the 2170 cell as presently used in some BEV. The presented multi-physics model has been formulated as a three-dimensional model to facilitate efficient and accurate numerical simulations in different conditions. Under general working conditions, the cells in a pack are exposed to a continuous charge/discharge load, where heat is generated inside the cells due to several electrochemical and degradation processes. The multi-physics modeling results in the form of the temperature profiles of the battery surface as well as the SEI formation/decomposition rate at various charge/discharge cycles are validated against the prior literature’s experimental data. Thermal images of the battery pack from different views are collected as sequences of video frames during the battery operation from multiple simulations to be used in DL. Based upon the multi-physics modeling results, Convolutional Neural Networks (CNNs) are proposed to predict the TRA-like events.3–5 Hyperparameters optimization has been performed to identify variables for the best performing ML method. The proposed combined multi-physics and machine learning modeling methodology provide interesting insight and predictive capabilities of the TRA. Thus, the developed combined multi-physics and ML modeling approach establishes a basis for 'on-the-fly' prediction of the TRA as well as a framework for extending machine learning methodologies to broad applications in battery failure prediction. References J. Newman and W. Tiedemann, J. Electrochem. Soc., 140, 1–5 (1993). X. Fen, X. He, M. Ouyang, L. Wang, L. Lu, D. Ren and S. Santhanagopalan, J. Electrochem. Soc., 165, A3748–A3765 (2018). J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., 2016-Decem, 779–788 (2016). K. He, X. Zhang, S. Ren, and J. Sun, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., 2016-Decem, 770–778 (2016). K. Simonyan and A. Zisserman, 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., 1–14 (2015).
- 9 October 2022
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2022-02 (3) , 230
Predicting Thermal Failures Using an Advanced Data-Driven Modeling Framework in a Cylindrical Li-Ion Battery Pack
Li-ion cells have been widely used in battery electric vehicles (BEV), hybrid electric vehicles (HEV), plug-in hybrid electric vehicles (PHEV), and stationary energy storage units due to their high specific energy and excellent cycle life. However, the safety of Li-ion battery (LIB) packs has become a vital issue, especially under extreme or abusive conditions. Fire and explosion due to the onset of thermal runaway often lead to catastrophic damages. Thermal failures are caused by drastic and successive processes and reactions that feed into one another, eventually leading to fire and explosion. Thus, one of the most crucial current research goals is to steer LIBs’ technology toward long-lasting and safe operation. In this work, we employ data-driven methods to predict and potentially prevent the thermal runaway (TRA) in a LIB battery pack with various cooling systems. Specifically, we use several deep learning (DL) techniques to learn and predict the likelihood of the TRA, using thermal images acquired from the multi-physics modeling of LIBs. The multi-physics modeling approach comprises a coupled thermal, electrochemical (P2D) model1 and degradation due to the solid electrolyte interface (SEI) formation/decomposition sub-models.2 The geometrical and material properties of the battery pack are taken from the 2170 cell as presently used in some BEV. The presented multi-physics model has been formulated as a three-dimensional model to facilitate efficient and accurate numerical simulations in different conditions. Under general working conditions, the cells in a pack are exposed to a continuous charge/discharge load, where heat is generated inside the cells due to several electrochemical and degradation processes. The multi-physics modeling results in the form of the temperature profiles of the battery surface as well as the SEI formation/decomposition rate at various charge/discharge cycles are validated against the prior literature’s experimental data. Thermal images of the battery pack from different views are collected as sequences of video frames during the battery operation from multiple simulations to be used in DL. Based upon the multi-physics modeling results, Convolutional Neural Networks (CNNs) are proposed to predict the TRA-like events.3–5 Hyperparameters optimization has been performed to identify variables for the best performing ML method. The proposed combined multi-physics and machine learning modeling methodology provide interesting insight and predictive capabilities of the TRA. Thus, the developed combined multi-physics and ML modeling approach establishes a basis for 'on-the-fly' prediction of the TRA as well as a framework for extending machine learning methodologies to broad applications in battery failure prediction. References J. Newman and W. Tiedemann, J. Electrochem. Soc., 140, 1–5 (1993). X. Fen, X. He, M. Ouyang, L. Wang, L. Lu, D. Ren and S. Santhanagopalan, J. Electrochem. Soc., 165, A3748–A3765 (2018). J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., 2016-Decem, 779–788 (2016). K. He, X. Zhang, S. Ren, and J. Sun, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., 2016-Decem, 770–778 (2016). K. Simonyan and A. Zisserman, 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., 1–14 (2015).
- 7 July 2022
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2022-01 (2) , 434
Advanced Data-Driven Modeling Framework for Predicting Thermal Failures in Li-Ion Pouch Batteries
With the rapid development and widespread applications of lithium-ion batteries (LIBs), there is an ongoing need to extend and apply theoretical models that assist LIB’s safety aspects. It is particularly important for electric vehicles (EVs) due to numerous recent fire accidents. Thermal runaway (TRA) is one of the principal causes of LIB’s failures in EVs occurring due to thermal or mechanical breakdown, internal/external short-circuiting, or electrochemical abuse. During EV’s operation, it is impossible to directly monitor the TRA; however, the change in thermo-electrical characteristics (pattern) during TRA-like events could signal the presence of a failure, allowing for the prediction of LIB malfunction. Thus, in this work, we employ machine learning-based techniques informed by multi-physics models to predict and prevent the TRA in large pouch LIBs as presently used in various EVs. The multi-physics model is implemented in commercial software Comsol, with the P2D electrochemical model1 and a 3D thermal model. The degradation sub-model2 includes oxygen release in the positive electrode to simulate the overcharge phenomenon during EV’s charging. In addition, the oxygen released in the positive electrode may exothermically react with the electrolyte as well as create significant stress in the electrode, which may lead to the mechanical deformation of the electrode and a subsequent TRA. An LG Chem lithium-ion pouch cell consisting of Li(Ni0.6Mn0.2Co0.2)O2 – NMC622 – cathode and graphite anode are studied to address this severe TRA problem. As a result of the time-varying nature of the variables that affect TRA, we propose three potential machine learning algorithms. These are Support Vector Machine, Deep Neural Network, and Recurrent Neural Network, tailored and implemented for estimating the TRA likelihood, using thermal images acquired from the multi-physics modeling of LIB pouch cells. Hyperparameters optimization has been performed to identify a set of variables for the best performing ML method. The proposed combined multi-physics and machine learning modeling methodology provide interesting insight and predictive capabilities for TRA prediction. References J. Newman and W. Tiedemann, J. Electrochem. Soc., 140, 1–5 (1993). X. Feng, X. He, M. Ouyang, L. Wang, L. Lu, D. Ren and S. Santhanagopalan, J. Electrochem. Soc., 165, A3748–A3765 (2018).
- 7 July 2022
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2022-01 (2) , 434
Advanced Data-Driven Modeling Framework for Predicting Thermal Failures in Li-Ion Pouch Batteries
With the rapid development and widespread applications of lithium-ion batteries (LIBs), there is an ongoing need to extend and apply theoretical models that assist LIB’s safety aspects. It is particularly important for electric vehicles (EVs) due to numerous recent fire accidents. Thermal runaway (TRA) is one of the principal causes of LIB’s failures in EVs occurring due to thermal or mechanical breakdown, internal/external short-circuiting, or electrochemical abuse. During EV’s operation, it is impossible to directly monitor the TRA; however, the change in thermo-electrical characteristics (pattern) during TRA-like events could signal the presence of a failure, allowing for the prediction of LIB malfunction. Thus, in this work, we employ machine learning-based techniques informed by multi-physics models to predict and prevent the TRA in large pouch LIBs as presently used in various EVs. The multi-physics model is implemented in commercial software Comsol, with the P2D electrochemical model1 and a 3D thermal model. The degradation sub-model2 includes oxygen release in the positive electrode to simulate the overcharge phenomenon during EV’s charging. In addition, the oxygen released in the positive electrode may exothermically react with the electrolyte as well as create significant stress in the electrode, which may lead to the mechanical deformation of the electrode and a subsequent TRA. An LG Chem lithium-ion pouch cell consisting of Li(Ni0.6Mn0.2Co0.2)O2 – NMC622 – cathode and graphite anode are studied to address this severe TRA problem. As a result of the time-varying nature of the variables that affect TRA, we propose three potential machine learning algorithms. These are Support Vector Machine, Deep Neural Network, and Recurrent Neural Network, tailored and implemented for estimating the TRA likelihood, using thermal images acquired from the multi-physics modeling of LIB pouch cells. Hyperparameters optimization has been performed to identify a set of variables for the best performing ML method. The proposed combined multi-physics and machine learning modeling methodology provide interesting insight and predictive capabilities for TRA prediction. References J. Newman and W. Tiedemann, J. Electrochem. Soc., 140, 1–5 (1993). X. Feng, X. He, M. Ouyang, L. Wang, L. Lu, D. Ren and S. Santhanagopalan, J. Electrochem. Soc., 165, A3748–A3765 (2018).
- 7 July 2022
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2022-01 (2) , 190
A Combined Multi-Physics Modelling and Machine Learning to Predict Electro-Thermal Failures of Cylindrical Li-Ion Batteries
Safety aspects of Li-ion batteries (LIBs) operation become increasingly important due to their integration into large-scale systems such as electric vehicles (EVs). Recent events involving many EVs explosions endangering consumers’ lives have shown that electro-thermal aspects of LIBs are far from being adequately managed. Thus, one of the most crucial goals of current research is to steer LIBs’ technology toward long-lasting and safe operation. In this work, we employ data-driven methods to predict and potentially prevent the thermal runaway (TRA) in LIBs. Specifically, we use various machine learning (ML) techniques to learn and predict the likelihood of the TRA, using thermal images acquired from the multi-physics modeling of LIBs. The multi-physics modeling approach is comprised of a coupled thermal, electrochemical (P2D) model1, and degradation due to the solid electrolyte interface (SEI) formation/decomposition sub-models.2 The presented multi-physics model has been formulated as a three-dimensional model to facilitate efficient and accurate numerical simulations in different conditions. Under general working conditions, the cell is exposed to a continuous charge/discharge load, where heat is generated inside the cell due to several electrochemical and degradation processes. Thermal images of the battery surface are collected as sequences of video frames during the battery operation from multiple simulations to be used in ML. LIB’s geometrical and material properties are taken from the 2170 cell as used in the current Tesla vehicles (model S 2021, model 3 2021). Based upon the multi-physics modeling results, two deep learning techniques, i.e., Convolutional Neural Networks (CNN) and object detection using YOLO, are proposed to address the problem of predicting the TRA like-events.3–5 The multi-physics modeling results in the form of the temperature profiles of the battery surface as well as the SEI formation/decomposition rate at various charge/discharge cycles are validated against the prior literature experimental data. Two regimes with single and double hot spots in the cylindrical LIB are investigated for a potential TRA occurrence. The CNN predictions of the TRA-like event on unknown data set show an excellent accuracy reaching up to 90% for all the different CNN architectures used. The object detection technique is found to be very efficient in identifying the location of TRA initiation at various conditions. Thus, the developed combined multi-physics and ML modeling approach establishes a basis for 'on-the-fly' prediction of the TRA as well as a framework for extending machine learning methodologies to broad applications in electrochemistry. References J. Newman and W. Tiedemann, J. Electrochem. Soc., 140, 1–5 (1993). X. Fen, X. He, M. Ouyang, L. Wang, L. Lu, D. Ren and S. Santhanagopalan, J. Electrochem. Soc., 165, A3748–A3765 (2018). J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., 2016-Decem, 779–788 (2016). K. He, X. Zhang, S. Ren, and J. Sun, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., 2016-Decem, 770–778 (2016). K. Simonyan and A. Zisserman, 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., 1–14 (2015).
- 7 July 2022
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2022-01 (2) , 190
A Combined Multi-Physics Modelling and Machine Learning to Predict Electro-Thermal Failures of Cylindrical Li-Ion Batteries
Safety aspects of Li-ion batteries (LIBs) operation become increasingly important due to their integration into large-scale systems such as electric vehicles (EVs). Recent events involving many EVs explosions endangering consumers’ lives have shown that electro-thermal aspects of LIBs are far from being adequately managed. Thus, one of the most crucial goals of current research is to steer LIBs’ technology toward long-lasting and safe operation. In this work, we employ data-driven methods to predict and potentially prevent the thermal runaway (TRA) in LIBs. Specifically, we use various machine learning (ML) techniques to learn and predict the likelihood of the TRA, using thermal images acquired from the multi-physics modeling of LIBs. The multi-physics modeling approach is comprised of a coupled thermal, electrochemical (P2D) model1, and degradation due to the solid electrolyte interface (SEI) formation/decomposition sub-models.2 The presented multi-physics model has been formulated as a three-dimensional model to facilitate efficient and accurate numerical simulations in different conditions. Under general working conditions, the cell is exposed to a continuous charge/discharge load, where heat is generated inside the cell due to several electrochemical and degradation processes. Thermal images of the battery surface are collected as sequences of video frames during the battery operation from multiple simulations to be used in ML. LIB’s geometrical and material properties are taken from the 2170 cell as used in the current Tesla vehicles (model S 2021, model 3 2021). Based upon the multi-physics modeling results, two deep learning techniques, i.e., Convolutional Neural Networks (CNN) and object detection using YOLO, are proposed to address the problem of predicting the TRA like-events.3–5 The multi-physics modeling results in the form of the temperature profiles of the battery surface as well as the SEI formation/decomposition rate at various charge/discharge cycles are validated against the prior literature experimental data. Two regimes with single and double hot spots in the cylindrical LIB are investigated for a potential TRA occurrence. The CNN predictions of the TRA-like event on unknown data set show an excellent accuracy reaching up to 90% for all the different CNN architectures used. The object detection technique is found to be very efficient in identifying the location of TRA initiation at various conditions. Thus, the developed combined multi-physics and ML modeling approach establishes a basis for 'on-the-fly' prediction of the TRA as well as a framework for extending machine learning methodologies to broad applications in electrochemistry. References J. Newman and W. Tiedemann, J. Electrochem. Soc., 140, 1–5 (1993). X. Fen, X. He, M. Ouyang, L. Wang, L. Lu, D. Ren and S. Santhanagopalan, J. Electrochem. Soc., 165, A3748–A3765 (2018). J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., 2016-Decem, 779–788 (2016). K. He, X. Zhang, S. Ren, and J. Sun, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., 2016-Decem, 770–778 (2016). K. Simonyan and A. Zisserman, 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., 1–14 (2015).
- 7 July 2022
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2022-01 (2) , 251
Revealing the Structure and Properties of Polycrystalline Components of the Solid Electrolyte Interface
The formation, structure and composition of the solid-electrolyte interphase (SEI) in lithium batteries have been extensively explored in the prior literature. It is commonly accepted that the SEI consists of two inorganic layer followed by organic layer. However, very little is known about the actual grain boundary (GB) structure of the inorganic layer and the ions transport through it. The present work seeks to understand the structure and stability of the GBs formed between various inorganic components of the SEI and mechanisms of Li diffusion through them. The density functional theory (DFT) calculations supported by the high-resolution transmission electron microscopy (HRTEM) measurements are employed to understand the SEI GB atomic structures and their chemo-mechanical properties. DFT calculations were performed using the Vienna Ab Initio Simulations Package (VASP) code1 employing the generalized-gradient approximation (GGA) using the PBE (Perdew, Burke, and Ernzerhof)2 functional to account for the exchange-correlation effects. The Nudged Elastic Band (NEB) method3 is used for the Li migration barriers calculations as implemented in VASP. To build the GB structures, the Atomistic Tool Kit (ATK)4 “Interface Builder” tool is used, which allows to analyze all possible interphases between two slabs. Cryogenic TEM (Cryo-TEM) images are recorded on a JEOL ARM200CF TEM, equipped with a Gatan Oneview camera operated at 200 kV. The HRTEM measurements revealed the polycrystalline structure of the SEI inorganic layer consisting mainly of LiF, Li2CO3, Li2O and LiOH components. In addition, different surface orientations (e.g., 111, 200, 002, etc.) of the aforementioned components are identified. Based upon the HRTEM results (cf. Fig. 1 left-hand side), the corresponding computational slabs have been built as shown on the right-hand side in Fig. 1. After the optimization of all structures, Li adatom diffusion inside grain and GB and mechanical properties were calculated. For each GB, several Li adatom positions with multi-atom bonding were identified. The activation energy of Li diffusion varies significantly depending upon the slab’s structure and the number of Li adatoms. The NEB calculations also reveal a non-symmetric transition state for all considered structures, which indicates a complex multi-atom hopping mechanism. The calculated elastic properties show the decrease of Young’s modulus with an increase of Li adatoms. Our combined experimental and modeling findings provide valuable insights into developing mitigation strategies towards a better understanding of the SEI components stability and Li migration through the SEI. Figure 1. Identification of grain and GB of the SEI busing HRTEM (left) and the corresponding built DFT slab (right). Lavender spheres denote Li atoms, red spheres are the oxygen atoms, grey spheres represent carbon atoms and green spheres are F atoms. Blue sphere in the GB denotes Li adatom. References G. Kresse, Phys. Rev. B, 59, 1758–1775 (1999). J. P. Perdew, A. Ruzsinszky, G. I. Csonka, O. A. Vydrov, G. E. Scuseria, L. A. Constantin, X. Zhou, K. Burke, Phys. Rev. Lett., 100, 136406 (2007). G. Henkelman, B. P. Uberuaga, H. Jónsson, and G. Henkelman, J. Chem. Phys, 113 9901 (2020). Synopsys QuantumWise A/S, 2017/2. Figure 1
- 7 July 2022
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2022-01 (2) , 251
Revealing the Structure and Properties of Polycrystalline Components of the Solid Electrolyte Interface
The formation, structure and composition of the solid-electrolyte interphase (SEI) in lithium batteries have been extensively explored in the prior literature. It is commonly accepted that the SEI consists of two inorganic layer followed by organic layer. However, very little is known about the actual grain boundary (GB) structure of the inorganic layer and the ions transport through it. The present work seeks to understand the structure and stability of the GBs formed between various inorganic components of the SEI and mechanisms of Li diffusion through them. The density functional theory (DFT) calculations supported by the high-resolution transmission electron microscopy (HRTEM) measurements are employed to understand the SEI GB atomic structures and their chemo-mechanical properties. DFT calculations were performed using the Vienna Ab Initio Simulations Package (VASP) code1 employing the generalized-gradient approximation (GGA) using the PBE (Perdew, Burke, and Ernzerhof)2 functional to account for the exchange-correlation effects. The Nudged Elastic Band (NEB) method3 is used for the Li migration barriers calculations as implemented in VASP. To build the GB structures, the Atomistic Tool Kit (ATK)4 “Interface Builder” tool is used, which allows to analyze all possible interphases between two slabs. Cryogenic TEM (Cryo-TEM) images are recorded on a JEOL ARM200CF TEM, equipped with a Gatan Oneview camera operated at 200 kV. The HRTEM measurements revealed the polycrystalline structure of the SEI inorganic layer consisting mainly of LiF, Li2CO3, Li2O and LiOH components. In addition, different surface orientations (e.g., 111, 200, 002, etc.) of the aforementioned components are identified. Based upon the HRTEM results (cf. Fig. 1 left-hand side), the corresponding computational slabs have been built as shown on the right-hand side in Fig. 1. After the optimization of all structures, Li adatom diffusion inside grain and GB and mechanical properties were calculated. For each GB, several Li adatom positions with multi-atom bonding were identified. The activation energy of Li diffusion varies significantly depending upon the slab’s structure and the number of Li adatoms. The NEB calculations also reveal a non-symmetric transition state for all considered structures, which indicates a complex multi-atom hopping mechanism. The calculated elastic properties show the decrease of Young’s modulus with an increase of Li adatoms. Our combined experimental and modeling findings provide valuable insights into developing mitigation strategies towards a better understanding of the SEI components stability and Li migration through the SEI. Figure 1. Identification of grain and GB of the SEI busing HRTEM (left) and the corresponding built DFT slab (right). Lavender spheres denote Li atoms, red spheres are the oxygen atoms, grey spheres represent carbon atoms and green spheres are F atoms. Blue sphere in the GB denotes Li adatom. References G. Kresse, Phys. Rev. B, 59, 1758–1775 (1999). J. P. Perdew, A. Ruzsinszky, G. I. Csonka, O. A. Vydrov, G. E. Scuseria, L. A. Constantin, X. Zhou, K. Burke, Phys. Rev. Lett., 100, 136406 (2007). G. Henkelman, B. P. Uberuaga, H. Jónsson, and G. Henkelman, J. Chem. Phys, 113 9901 (2020). Synopsys QuantumWise A/S, 2017/2. Figure 1
- Open Access
- 1 January 2022
- Published by Elsevier in SSRN Electronic Journal
A Combined Multiphysics Modeling and Deep Learning Framework to Predict Thermal Runaway in Cylindrical Li-Ion Batteries
In this paper, we employ deep learning (DL) modeling to predict the thermal runaway (TRA) occurrence in Li-ion batteries (LIBs). State-of-the-art convolutional neural networks (CNNs) are adopted to forecast the evolution of TRA phenomenon with a classification approach of three distinct stages, namely, safe operation, critical condition of triggered TRA and the actual TRA occurrence. In addition, the “you look only once” (YOLO) object detection DL model is used to identify the location of the TRA heat sources within the battery. The neural networks are trained on simulated thermal images, computed with the multiphysics modeling of LIBs. The multiphysics modeling approach comprises a coupled thermal, electrochemical (P2D model) and degradation sub-models. The degradation phenomenon, leading to the TRA considered in this paper, is the solid electrolyte interface (SEI) formation/decomposition on the negative electrode. The proposed DL model exhibits high accuracy in predicting the TRA evolution stages and heat source locations. The combined multiphysics and DL modeling approach developed in this work, provides qualitative insights for 'on-the-fly' prediction of the TRA, as well as a framework for extending data-driven methodologies to broad applications in electrochemistry.
- 1 January 2022
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Combined Multiphysics Modeling and Deep Learning Framework to Predict Thermal Runaway in Cylindrical Li-Ion Batteries
In this paper, we employ deep learning (DL) modeling to predict the thermal runaway (TRA) occurrence in Li-ion batteries (LIBs). State-of-the-art convolutional neural networks (CNNs) are adopted to forecast the evolution of TRA phenomenon with a classification approach of three distinct stages, namely, safe operation, critical condition of triggered TRA and the actual TRA occurrence. In addition, the “you look only once” (YOLO) object detection DL model is used to identify the location of the TRA heat sources within the battery. The neural networks are trained on simulated thermal images, computed with the multiphysics modeling of LIBs. The multiphysics modeling approach comprises a coupled thermal, electrochemical (P2D model) and degradation sub-models. The degradation phenomenon, leading to the TRA considered in this paper, is the solid electrolyte interface (SEI) formation/decomposition on the negative electrode. The proposed DL model exhibits high accuracy in predicting the TRA evolution stages and heat source locations. The combined multiphysics and DL modeling approach developed in this work, provides qualitative insights for 'on-the-fly' prediction of the TRA, as well as a framework for extending data-driven methodologies to broad applications in electrochemistry.