Théo Heitzmann
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Théo Heitzmann has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
Ahmed Samet
INSA Strasbourg, ICube Laboratory UMR 7357 and CNRS, Universit de Strasbourg, Strasbourg, France
2 shared publicationsRomuald Boné
INSA Strasbourg, ICube Laboratory UMR 7357 and CNRS, Universit de Strasbourg, Strasbourg, France
2 shared publications- Tedjani Mesbahi
INSA Strasbourg, ICube Laboratory UMR 7357 and CNRS, Universit de Strasbourg, Strasbourg, France
2 shared publications Ali Ayadi
INSA Strasbourg, ICube Laboratory UMR 7357 and CNRS, Universit de Strasbourg, Strasbourg, France
1 shared publicationAmel Hidouri
Institut Marey Maison de la Mtallurgie (I3M), Universit Bourgogne Europe, Dijon, France
1 shared publicationLakhdar Mamouri
INSA Strasbourg, ICube Laboratory UMR 7357 and CNRS, Universit de Strasbourg, Strasbourg, France
1 shared publication
Latest Publications
- 9 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Prédiction explicable du vieillissement des batteries lithium-ion pour une prolongation intelligente de leur durée de vie dans le domaine de la mobilité électrique
Les batteries lithium-ion représentent un atout clé dans la transition énergétique, alimentant les véhicules électriques et permettant le stockage d’énergie stationnaire. Cependant, leur production dépend de matières premières critiques qui sont des ressources limitées et de plus en plus rares. Pour pallier cette contrainte, il est essentiel de prolonger la durée de vie des batteries en limitant leur dégradation. Cela nécessite une compréhension approfondie des facteurs accélérant le vieillissement des batteries ainsi que des stratégies permettant d’optimiser leur utilisation. Dans ce contexte, la prédiction de l'état de santé (State of Health - SOH) des batteries devient un enjeu essentiel. Le SOH peut être évalué à partir de deux phénomènes principaux liés au vieillissement de la batterie : la perte de capacité et l’augmentation de la résistance interne. Cet indicateur permet alors d'anticiper les performances énergétiques des batteries et les maintenances ainsi que d'optimiser leur utilisation et leur sécurité. Cette thèse se focalise sur la construction de modèles d'apprentissage profond de prédiction de la dégradation des batteries à partir de jeux de données sur leur vieillissement. Ces modèles sont rendus explicables grâce à des méthodes issues du domaine de l'explicabilité de l'IA. Les explications produites permettent d'interpréter les prédictions du modèle et d'identifier des indicateurs indirects de la dégradation des batteries et les facteurs qui l'accélèrent.
- 9 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Prédiction explicable du vieillissement des batteries lithium-ion pour une prolongation intelligente de leur durée de vie dans le domaine de la mobilité électrique
Les batteries lithium-ion représentent un atout clé dans la transition énergétique, alimentant les véhicules électriques et permettant le stockage d’énergie stationnaire. Cependant, leur production dépend de matières premières critiques qui sont des ressources limitées et de plus en plus rares. Pour pallier cette contrainte, il est essentiel de prolonger la durée de vie des batteries en limitant leur dégradation. Cela nécessite une compréhension approfondie des facteurs accélérant le vieillissement des batteries ainsi que des stratégies permettant d’optimiser leur utilisation. Dans ce contexte, la prédiction de l'état de santé (State of Health - SOH) des batteries devient un enjeu essentiel. Le SOH peut être évalué à partir de deux phénomènes principaux liés au vieillissement de la batterie : la perte de capacité et l’augmentation de la résistance interne. Cet indicateur permet alors d'anticiper les performances énergétiques des batteries et les maintenances ainsi que d'optimiser leur utilisation et leur sécurité. Cette thèse se focalise sur la construction de modèles d'apprentissage profond de prédiction de la dégradation des batteries à partir de jeux de données sur leur vieillissement. Ces modèles sont rendus explicables grâce à des méthodes issues du domaine de l'explicabilité de l'IA. Les explications produites permettent d'interpréter les prédictions du modèle et d'identifier des indicateurs indirects de la dégradation des batteries et les facteurs qui l'accélèrent.
- Open Access
- 14 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Vehicular Technology
- Vol. 7, 510-522
Spiking Neural Networks for Accurate and Efficient State of Health Estimation of Lithium-Ion Batteries Across Varying Temperatures
Machine learning (ML) and deep learning (DL) have become essential tools in lithium-ion battery research, particularly for estimating the State of Health (SOH). However, conventional SOH estimation methods often rely on repeated charge/discharge cycles under strictly controlled laboratory conditions, limiting their applicability in real world scenarios. In this study, we present a comprehensive lithium-ion battery dataset developed by our team to support data driven approaches for battery diagnostics and predictive modeling. The dataset comprises nineteen lithium iron phosphate (LFP) cells with cycle lifetimes ranging from 500 to 2600 cycles and reflects realistic usage conditions, including non constant discharge currents and tests conducted at $25\,^\circ \text{C}$, $35\,^\circ \text{C}$, and $45\,^\circ \text{C}$. To demonstrate the utility of this dataset, we used a brain inspired Spiking Neural Network (SNN) referred to as SpikeSOH, a neuromorphic model that uses sparse, time coded spikes to mimic biological neurons. This approach provides temporal precision while reducing energy consumption. Our results show that the SNN-based model achieves an average Mean Absolute Error (MAE) of 4.5%, while also outperforming conventional deep learning models in computational efficiency, with an average inference time of 3.55 $\mu \mathrm{s}$ and an average energy consumption of 0.36 mJ. These characteristics make the model particularly suitable for integration into energy constrained battery management systems. By providing a realistic, high quality dataset and demonstrating the advantages of energy efficient neuromorphic models, this work advances accurate and scalable SOH estimation methods, helping safer and more reliable deployment of lithium-ion batteries in both first life and second life applications.
- 14 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Vehicular Technology
- Vol. 7, 510-522
Open AccessSpiking Neural Networks for Accurate and Efficient State of Health Estimation of Lithium-Ion Batteries Across Varying Temperatures
Machine learning (ML) and deep learning (DL) have become essential tools in lithium-ion battery research, particularly for estimating the State of Health (SOH). However, conventional SOH estimation methods often rely on repeated charge/discharge cycles under strictly controlled laboratory conditions, limiting their applicability in real world scenarios. In this study, we present a comprehensive lithium-ion battery dataset developed by our team to support data driven approaches for battery diagnostics and predictive modeling. The dataset comprises nineteen lithium iron phosphate (LFP) cells with cycle lifetimes ranging from 500 to 2600 cycles and reflects realistic usage conditions, including non constant discharge currents and tests conducted at $25\,^\circ \text{C}$, $35\,^\circ \text{C}$, and $45\,^\circ \text{C}$. To demonstrate the utility of this dataset, we used a brain inspired Spiking Neural Network (SNN) referred to as SpikeSOH, a neuromorphic model that uses sparse, time coded spikes to mimic biological neurons. This approach provides temporal precision while reducing energy consumption. Our results show that the SNN-based model achieves an average Mean Absolute Error (MAE) of 4.5%, while also outperforming conventional deep learning models in computational efficiency, with an average inference time of 3.55 $\mu \mathrm{s}$ and an average energy consumption of 0.36 mJ. These characteristics make the model particularly suitable for integration into energy constrained battery management systems. By providing a realistic, high quality dataset and demonstrating the advantages of energy efficient neuromorphic models, this work advances accurate and scalable SOH estimation methods, helping safer and more reliable deployment of lithium-ion batteries in both first life and second life applications.
- Open Access
- 18 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Vehicular Technology
- Vol. 7, 144-159
Time Series-Based Explainable Model for Lithium-Ion Battery State of Health Prediction
Lithium-ion batteries are pivotal to the energy transition, powering electric vehicles and enabling stationary energy storage systems. However, their reliance on finite and scarce materials underscores the need for improved sustainability. Extending battery lifetime by mitigating degradation mechanisms is therefore essential to enhance performance, reduce resource dependency, and support large-scale energy deployment. That requires a thorough understanding of the factors that accelerate battery aging and the strategies to optimize their usage. To that end, we propose a model for predicting the state of health of the lithium-ion battery based on a combination of convolution, Transformers and Bi-LSTM (Long Short-Term Memory), which involves using explainability methods in order to understand the inner workings and reasoning of the model. That approach predicts the capacity degradation curve from a sliding window of time series, each made up of 3 charge and discharge cycles of our laboratory dataset including current, voltage, temperature and state of charge (SOC). An extension of Shapley values for time series adapted to the problem of battery aging is proposed, allowing the study of the influence of the model input parameters from multiple perspectives, including state of charge, temperature dynamics, and current regimes. Those Shapley values quantify the influence of individual features on the battery aging rate, thereby enabling the identification of usage patterns that contribute to accelerated degradation.
- 18 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Vehicular Technology
- Vol. 7, 144-159
Open AccessTime Series-Based Explainable Model for Lithium-Ion Battery State of Health Prediction
Lithium-ion batteries are pivotal to the energy transition, powering electric vehicles and enabling stationary energy storage systems. However, their reliance on finite and scarce materials underscores the need for improved sustainability. Extending battery lifetime by mitigating degradation mechanisms is therefore essential to enhance performance, reduce resource dependency, and support large-scale energy deployment. That requires a thorough understanding of the factors that accelerate battery aging and the strategies to optimize their usage. To that end, we propose a model for predicting the state of health of the lithium-ion battery based on a combination of convolution, Transformers and Bi-LSTM (Long Short-Term Memory), which involves using explainability methods in order to understand the inner workings and reasoning of the model. That approach predicts the capacity degradation curve from a sliding window of time series, each made up of 3 charge and discharge cycles of our laboratory dataset including current, voltage, temperature and state of charge (SOC). An extension of Shapley values for time series adapted to the problem of battery aging is proposed, allowing the study of the influence of the model input parameters from multiple perspectives, including state of charge, temperature dynamics, and current regimes. Those Shapley values quantify the influence of individual features on the battery aging rate, thereby enabling the identification of usage patterns that contribute to accelerated degradation.