Publications

2024

1. 

   DiffBatt: A Diffusion Model for Battery Degradation Prediction and Synthesis

   Hamidreza Eivazi, André Hebenbrock, Raphael Ginster , and 6 more authors

   In Neurips 2024 Workshop Foundation Models for Science: Progress, Opportunities, and Challenges , 2024

   Abs HTML PDF Code

   Battery degradation remains a critical challenge in the pursuit of green technologies and sustainable energy solutions. Despite significant research efforts, predicting battery capacity loss accurately remains a formidable task due to its complex nature, influenced by both aging and cycling behaviors. To address this challenge, we introduce a novel general-purpose model for battery degradation prediction and synthesis, DiffBatt. Leveraging an innovative combination of conditional and unconditional diffusion models with classifier-free guidance and transformer architecture, DiffBatt achieves high expressivity and scalability. DiffBatt operates as a probabilistic model to capture uncertainty in aging behaviors and a generative model to simulate battery degradation. The performance of the model excels in prediction tasks while also enabling the generation of synthetic degradation curves, facilitating enhanced model training by data augmentation. In the remaining useful life prediction task, DiffBatt provides accurate results with a mean RMSE of 196 cycles across all datasets, outperforming all other models and demonstrating superior generalizability. This work represents an important step towards developing foundational models for battery degradation.

2. Physics-informed deep-learning applications to experimental fluid mechanics

   Hamidreza Eivazi, Yuning Wang, and Ricardo Vinuesa

   Measurement science and technology, 2024

3. 

   Nonlinear model reduction for operator learning

   Hamidreza Eivazi, Stefan Wittek, and Andreas Rausch

   Tiny Papers @ ICLR 2024 Notable, 2024

   Abs HTML PDF Code

   Operator learning provides methods to approximate mappings between infinite-dimensional function spaces. Deep operator networks (DeepONets) are a notable architecture in this field. Recently, an extension of DeepONet based on model reduction and neural networks, proper orthogonal decomposition (POD)-DeepONet, has been able to outperform other architectures in terms of accuracy for several benchmark tests. We extend this idea towards nonlinear model order reduction by proposing an efficient framework that combines neural networks with kernel principal component analysis (KPCA) for operator learning. Our results demonstrate the superior performance of KPCA-DeepONet over POD-DeepONet.

4. Thunderstorm prediction during pre-tactical air-traffic-flow management using convolutional neural networks

   Aniel Jardines, Hamidreza Eivazi, Elias Zea , and 5 more authors

   Expert systems with applications, 2024
5. Enhancing multiscale simulations with constitutive relations-aware deep operator networks

   Hamidreza Eivazi, Mahyar Alikhani, Jendrik-Alexander Tröger , and 3 more authors

   PAMM, 2024

   Abs HTML

   Abstract Multiscale problems are widely observed across diverse domains in physics and engineering. Translating these problems into numerical simulations and solving them using numerical schemes, for example, the finite element method, is costly due to the demand of solving initial boundary-value problems at multiple scales. On the other hand, multiscale finite element computations are commended for their ability to integrate micro-structural properties into macroscopic computational analyses using homogenization techniques. Recently, neural operator-based surrogate models have shown trustworthy performance for solving a wide range of partial differential equations. In this work, we propose a hybrid method in which we utilize deep operator networks for surrogate modeling of the microscale physics. This allows us to embed the constitutive relations of the microscale into the model architecture and to predict microscale strains and stresses based on the prescribed macroscale strain inputs. Furthermore, numerical homogenization is carried out to obtain the macroscale quantities of interest. We apply the proposed approach to quasi-static problems of solid mechanics. The results demonstrate that our constitutive relations-aware DeepONet can yield accurate solutions even when being confronted with a restricted dataset during model development.

2023

1. FE2 computations with deep neural networks: algorithmic structure, data generation, and implementation

   Hamidreza Eivazi, Jendrik-Alexander Tröger, Stefan Wittek , and 2 more authors

   Mathematical and Computational Applications, 2023
2. Enhancement of PIV measurements via physics-informed neural networks

   Gazi Hasanuzzaman, Hamidreza Eivazi, Sebastian Merbold , and 2 more authors

   Measurement Science and Technology, 2023
3. Sentiment analysis on Twitter data towards climate action

   Emelie Rosenberg, Carlota Tarazona, Fermı́n Mallor , and 4 more authors

   Results in Engineering, 2023
4. The sustainable development goals and aerospace engineering: a critical note through artificial intelligence

   Alejandro Sánchez-Roncero, Òscar Garibo-i-Orts, J Alberto Conejero , and 7 more authors

   Results in Engineering, 2023
5. The potential of artificial intelligence for achieving healthy and sustainable societies

   Beril Sirmaçek, S Gupta, Fermı́n Mallor , and 8 more authors

   In The ethics of artificial intelligence for the sustainable development goals , 2023
6. Efficient integration of deep neural networks in sequential multiscale simulations

   Jendrik-Alexander Tröger, Hamidreza Eivazi, Stefan Hartmann , and 2 more authors

   PAMM, 2023

2022

1. 

   Physics-informed neural networks for solving Reynolds-averaged Navier–Stokes equations

   Hamidreza Eivazi, Mojtaba Tahani, Philipp Schlatter , and 1 more author

   Physics of Fluids, Jul 2022

   Abs HTML PDF Code

   Physics-informed neural networks (PINNs) are successful machine-learning methods for the solution and identification of partial differential equations. We employ PINNs for solving the Reynolds-averaged Navier–Stokes equations for incompressible turbulent flows without any specific model or assumption for turbulence and by taking only the data on the domain boundaries. We first show the applicability of PINNs for solving the Navier–Stokes equations for laminar flows by solving the Falkner–Skan boundary layer. We then apply PINNs for the simulation of four turbulent-flow cases, i.e., zero-pressure-gradient boundary layer, adverse-pressure-gradient boundary layer, and turbulent flows over a NACA4412 airfoil and the periodic hill. Our results show the excellent applicability of PINNs for laminar flows with strong pressure gradients, where predictions with less than 1\% error can be obtained. For turbulent flows, we also obtain very good accuracy on simulation results even for the Reynolds-stress components.

2. 

   Towards extraction of orthogonal and parsimonious non-linear modes from turbulent flows

   Hamidreza Eivazi, Soledad Le Clainche, Sergio Hoyas , and 1 more author

   Expert Systems with Applications, Jul 2022

   Abs HTML PDF Code

   Modal-decomposition techniques are computational frameworks based on data aimed at identifying a low-dimensional space for capturing dominant flow features: the so-called modes. We propose a deep probabilistic-neural-network architecture for learning a minimal and near-orthogonal set of non-linear modes from high-fidelity turbulent-flow data useful for flow analysis, reduced-order modeling and flow control. Our approach is based on β-variational autoencoders (β-VAEs) and convolutional neural networks (CNNs), which enable extracting non-linear modes from multi-scale turbulent flows while encouraging the learning of independent latent variables and penalizing the size of the latent vector. Moreover, we introduce an algorithm for ordering VAE-based modes with respect to their contribution to the reconstruction. We apply this method for non-linear mode decomposition of the turbulent flow through a simplified urban environment, where the flow-field data is obtained based on well-resolved large-eddy simulations (LESs). We demonstrate that by constraining the shape of the latent space, it is possible to motivate the orthogonality and extract a set of parsimonious modes sufficient for high-quality reconstruction. Our results show the excellent performance of the method in the reconstruction against linear-theory-based decompositions, where the energy percentage captured by the proposed method from five modes is equal to 87.36% against 32.41% of the POD. Moreover, we compare our method with available AE-based models. We show the ability of our approach in the extraction of near-orthogonal modes with the determinant of the correlation matrix equal to 0.99, which may lead to interpretability.

3. Predicting the temporal dynamics of turbulent channels through deep learning

   Giuseppe Borrelli, Luca Guastoni, Hamidreza Eivazi , and 2 more authors

   International Journal of Heat and Fluid Flow, Jul 2022
4. Non-Linear Orthogonal Modal Decompositions in Turbulent Flows via Autoencoders

   Hamidreza Eivazi, Soledad Le Clainche, Sergio Hoyas , and 1 more author

   In 12th International Symposium on Turbulence and Shear Flow Phenomena, TSFP 2022, Osaka/Virtual, Japan, 19-22 July 2022 , Jul 2022
5. β-Variational autoencoders for nonlinear and ortogonal reduced-order models in turbulence

   Ricardo Vinuesa, Hamidreza Eivazi, Soledad Le Clainche , and 1 more author

   Bulletin of the American Physical Society, Jul 2022

2021

1. Recurrent neural networks and Koopman-based frameworks for temporal predictions in a low-order model of turbulence

   Hamidreza Eivazi, Luca Guastoni, Philipp Schlatter , and 2 more authors

   International Journal of Heat and Fluid Flow, Jul 2021

2020

1. Deep neural networks for nonlinear model order reduction of unsteady flows

   Hamidreza Eivazi, Hadi Veisi, Mohammad Hossein Naderi , and 1 more author

   Physics of Fluids, Jul 2020
2. Analysis and prediction of gas turbine performance with evaporative cooling processes by developing a stage stacking algorithm

   Mirhamed Salehi, Hamidreza Eivazi, Mojtaba Tahani , and 1 more author

   Journal of Cleaner Production, Jul 2020
3. An experimental study on boundary layer transition detection over a pitching supercritical airfoil using hot-film sensors

   Arshia Tabrizian, Massoud Tatar, Mehran Masdari , and 2 more authors

   International Journal of Heat and Fluid Flow, Jul 2020

2019

1. New method for dynamic mode decomposition of flows over moving structures based on machine learning (hybrid dynamic mode decomposition)

   Mohammad Hossein Naderi, Hamidreza Eivazi, and Vahid Esfahanian

   Physics of Fluids, Jul 2019

2017

1. Assessment of turbulence models for transonic oscillating airfoil

   Mojtaba Tahani, Mehran Masdari, Hamidreza Eivazi , and 1 more author

   International Journal of Numerical Methods for Heat & Fluid Flow, Jul 2017