Georgios Tsialiamanis
Department of Mechanical Engineering
Lecturer in Mechanical Engineering
g.tsialiamanis@sheffield.ac.uk
Sir Frederick Mappin Building
Full contact details
Georgios Tsialiamanis
Department of Mechanical Engineering
Sir Frederick Mappin Building
Mappin Street
Sheffield
S1 3JD
Department of Mechanical Engineering
Sir Frederick Mappin Building
Mappin Street
Sheffield
S1 3JD
- Profile
-
I completed my PhD at the University of Sheffield from 2018 until 2021 and the title of this was "A data-driven approach to modelling structures".
After completing my PhD, I worked as a postdoc for 2 years at the Dynamics Research Group of the University of Sheffield before taking my position as a Lecturer in the same group.
Before starting my PhD, I did my MEng at the Civil Engineering Department of the National Technical University of Athens in Greece, where I come from, and after completing my studies, I worked for a year in industry as a simulation engineer.
- Research interests
-
My research interests include:
- Machine learning for modelling structural dynamics
- Structural health monitoring and population-based structural health monitoring
- Use of different types of models and data for the creation of digital twins
- Publications
-
Journal articles
- On a meta-learning population-based approach to damage prognosis. Mechanical Systems and Signal Processing, 209, 111119-111119.
- Towards a population-informed approach to the definition of data-driven models for structural dynamics. Mechanical Systems and Signal Processing, 200. View this article in WRRO
- On the dynamic properties of statistically-independent nonlinear normal modes. Mechanical Systems and Signal Processing, 181. View this article in WRRO
- On the application of generative adversarial networks for nonlinear modal analysis. Mechanical Systems and Signal Processing, 166.
- On generative models as the basis for digital twins. Data-Centric Engineering, 2. View this article in WRRO
- Foundations of population-based SHM, Part IV : the geometry of spaces of structures and their feature spaces. Mechanical Systems and Signal Processing, 157. View this article in WRRO
Chapters
- On Modelling Statistically Independent Nonlinear Normal Modes with Gaussian Process NARX Models, Nonlinear Structures & Systems, Volume 1 (pp. 135-147). Springer International Publishing
- On the Use of Variational Autoencoders for Nonlinear Modal Analysis, Nonlinear Structures & Systems, Volume 1 (pp. 297-300). Springer International Publishing
- On the Use of Cycle-Consistent Generative Adversarial Networks for Nonlinear Modal Analysis, Topics in Modal Analysis & Parameter Identification, Volume 8 (pp. 45-57). Springer International Publishing
- Artificial Neural Networks, Computational Methods in Engineering & the Sciences (pp. 85-119). Springer International Publishing
- A Meta-Learning Approach to Population-Based Modelling of Structures, Data Science in Engineering, Volume 10 (pp. 63-71). Springer Nature Switzerland
- Bayesian Graph Neural Networks for Strain-Based Crack Localization, Data Science in Engineering, Volume 9 (pp. 253-261). Springer International Publishing
- On Generating Parametrised Structural Data Using Conditional Generative Adversarial Networks, Data Science in Engineering, Volume 9 (pp. 35-46). Springer International Publishing
- On an Application of Graph Neural Networks in Population-Based SHM, Data Science in Engineering, Volume 9 (pp. 47-63). Springer International Publishing
- An Evolutionary Approach to Learning Neural Networks for Structural Health Monitoring, Model Validation and Uncertainty Quantification, Volume 3 (pp. 237-246). Springer International Publishing
Conference proceedings papers
- On the detection and quantification of nonlinearity via statistics of the gradients of a black-box model. Nonlinear Structures & Systems, Volume 1: Proceedings of the 41st IMAC, A Conference and Exposition on Structural Dynamics 2023 (pp 1-9). Austin, TX United States, 13 February 2023 - 13 February 2023. View this article in WRRO
- On an application of generative adversarial networks on remaining lifetime estimation. Structural Health Monitoring 2021: Enabling Next Generation SHM for Cyber-Physical Systems: Proceedings of the Thirteenth International Workshop on Structural Health Monitoring (IWSHM). Stanford University, CA, USA, 15 March 2022 - 15 March 2022. View this article in WRRO
- An ontological approach to structural health monitoring. Topics in Modal Analysis & Testing, Volume 8 : Proceedings of the 38th IMAC, A Conference and Exposition on Structural Dynamics 2020, Vol. 8 (pp 51-59). Houston, TX, USA, 10 February 2020 - 13 February 2020.
- On partitioning of an SHM problem and parallels with transfer learning. Topics in Modal Analysis & Testing, Volume 8 : Proceedings of the 38th IMAC, A Conference and Exposition on Structural Dynamics 2020, Vol. 8 (pp 41-50). Houston, TX, USA, 10 February 2020 - 13 February 2020.
- An application of generative adversarial networks in structural health monitoring. EURODYN 2020: Proceedings of the XI International Conference on Structural Dynamics, Vol. 2 (pp 3816-3831). Athens, Greece, 23 November 2020 - 26 November 2020.
- A neat approach to structural health monitoring. EURODYN 2020: Proceedings of the XI International Conference on Structural Dynamics (pp 3832-3845). Athens, Greece, 23 November 2020 - 23 November 2020. View this article in WRRO
Preprints
- Towards a population-informed approach to the definition of data-driven models for structural dynamics, arXiv.
- On the Detection and Quantification of Nonlinearity via Statistics of the Gradients of a Black-Box Model, arXiv.
- A Meta-Learning Approach to Population-Based Modelling of Structures, arXiv.
- Towards a Population-Informed Approach to the Definition of Data-Driven Models for Structural Dynamics, Elsevier BV.
- On an Application of Generative Adversarial Networks on Remaining Lifetime Estimation, arXiv.
- On generative models as the basis for digital twins, arXiv.
- On partitioning of an SHM problem and parallels with transfer learning, arXiv.
- On generating parametrised structural data using conditional generative adversarial networks, arXiv.
- On an application of graph neural networks in population based SHM, arXiv.
- On the application of generative adversarial networks for nonlinear modal analysis, arXiv.
- Foundations of Population-Based SHM, Part IV: The Geometry of Spaces of Structures and their Feature Spaces, arXiv.
- Bayesian graph neural networks for strain-based crack localization, arXiv.
- On a meta-learning population-based approach to damage prognosis. Mechanical Systems and Signal Processing, 209, 111119-111119.
- Teaching activities
-
2023-2024: AER291: Dynamics of Structures and Machines (Aerospace)