Loading Session..

MS20.1: Physics-enhanced machine learning and data-driven nonlinear dynamics

Session Information

Jul 23, 2024 15:50 - 17:10(Europe/Amsterdam)
Venue : AULA - Commissiekamer 2
20240723T1550 20240723T1710 Europe/Amsterdam MS20.1: Physics-enhanced machine learning and data-driven nonlinear dynamics AULA - Commissiekamer 2 Enoc2024 n.fontein@tudelft.nl

Sub Sessions

Deep learning-based damage identification in nonlinear dynamical systems

MS-20 - Physics-enhanced machine learning and data-driven nonlinear dynamics 03:50 PM - 04:10 PM (Europe/Amsterdam) 2024/07/23 13:50:00 UTC - 2024/07/23 14:10:00 UTC
Deep learning algorithms can be employed to monitor and assess the actual conditions of civil and industrial structures before damage can cause detrimental effects on their safety or serviceability. Within this framework, the suitability of deep learning algorithms has been investigated for linear structures, while there is a lack of studies targeted at demonstrating their effectiveness for damage detection in nonlinear dynamical systems. In this perspective, the present study illustrates preliminary results concerning damage detection in a single-degree-of-freedom Duffing oscillator using a 1-dimensional convolutional autoencoder-based neural network architecture. The neural network training is carried out in an unsupervised manner to avoid the need for labeled databases. Numerical simulations demonstrate that the proposed computational strategy allows for the reliable identification of low damage levels in dynamical systems experiencing nonlinear behavior.
Presenters
HJ
Harrish Joseph
PhD, Sapienza University Of Rome
Co-Authors
BC
Biagio Carboni
Associate Professor, Sapienza University Of Rome
GQ
Giuseppe Quaranta
Associate Professor, Sapienza University
WL
Walter  Lacarbonara
Professor, University Of Rome

Hybrid simulation for physics-based and data-driven model integration: a rotor dynamics case study

MS-20 - Physics-enhanced machine learning and data-driven nonlinear dynamics 04:10 PM - 04:30 PM (Europe/Amsterdam) 2024/07/23 14:10:00 UTC - 2024/07/23 14:30:00 UTC
In this study, we investigate a Laval rotor dynamics scenario where the damping properties remain elusive. To address this challenge, we employ an artificial neural network to model the damping force, seamlessly integrating it into the governing equations of motion. Through direct time integration techniques, we analyse the system’s behaviour and delve into the frequency response function to elucidate the impact of incorporating data-driven models into simulations. This approach sheds light on the efficacy of leveraging neural networks to capture unknown physical phenomena, enhancing the accuracy and predictive capabilities of dynamics analyses. The case study showcases the potentials, but also pitfalls, of the direct integration of learning models into knowledge-based system descriptions.
Presenters
AZ
Anouk Zandbergen
PhD, Technische Universität Berlin
Co-Authors Merten Stender
Professor, Technische Universität Berlin

Augmenting state-space models with normalising flows for nonlinear normal mode decomposition

MS-20 - Physics-enhanced machine learning and data-driven nonlinear dynamics 04:30 PM - 04:50 PM (Europe/Amsterdam) 2024/07/23 14:30:00 UTC - 2024/07/23 14:50:00 UTC
Multiple-degree-of-freedom (MDOF) linear dynamical systems can be exactly decomposed into single-degree-of-freedom (SDOF) oscillators via proper orthogonal decomposition (POD); however, techniques based on linear mappings do not generalise to nonlinear systems. Machine learning approaches have been proposed as a means to decompose/decouple nonlinear systems via nonlinear transformations. Normalising flows (NFs) map complex distributions onto a simplified, user-defined latent space. The current work proposes an augmented linear state-space model as the target space, and uses continuous NFs to solve a neural ordinary differential equation (ODE) that defines the nonlinear map from the data distribution to the latent, decomposed space. This approach is demonstrated using a simulated two-degree-of-freedom (2DOF), lumped-mass system with a cubic spring.
Presenters
TD
Tina Dardeno
Research Associate , The University Of Sheffield
Co-Authors
LB
Lawrence Bull
The University Of Cambridge
ND
Nikolaos Dervilis
The University Of Sheffield
KW
Keith Worden
The University Of Sheffield

On the Design of Metastructures for Low-Frequency Vibration Attenuation

MS-20 - Physics-enhanced machine learning and data-driven nonlinear dynamics 04:50 PM - 05:10 PM (Europe/Amsterdam) 2024/07/23 14:50:00 UTC - 2024/07/23 15:10:00 UTC
This study deals with the design of distributed internal oscillators in a metastructure to achieve its beneficial low-frequency vibration performance. First, an analytical approach is taken in which all of them are equal mutually and tuned to the first resonance of the metastructure with blocked internal oscillators. As tuning to the second resonance frequency of the metastructure of this shape could not be achieved practically, a physics-based machine learning approach is developed to design absorbers of different size and distribution along the metastructure, targeting the widest possible low-frequency vibration attenuation regions around the first and second resonance simultaneously. Such metastructure is then fabricated and its beneficial performance is verified experimentally.
Presenters Ivana Kovacic
Head Of The Centre Of Excellence CEVAS, University Of Novi Sad, Faculty Of Technical Sciences, CEVAS
Co-Authors
ZK
Zeljko Kanovic
University Of Novi Sad, Faculty Of Technical Science
VR
Vladimir Rajs
University Of Novi Sad, Faculty Of Technical Sciences
LT
Lj Teofanov
University Of Novi Sad, Faculty Of Technical Sciences

High-Aspect-Ratio Mechanics: New Dimensions in Nanotechnology & Machine Learning

05:10 PM - 05:30 PM (Europe/Amsterdam) 2024/07/23 15:10:00 UTC - 2024/07/23 15:30:00 UTC
Over the past fifty years, Moore's Law has guided nanotechnology towards the miniaturization of components across all three dimensions: x, y, and z. As we near its limits in 2025, our laboratory is investigating a novel form of nanotechnology with components that extend over large distances in the x and y dimensions while maintaining nanoscale thickness in the z dimension. These extreme-aspect-ratio nanostructures possess a unique blend of macro- and nano-features, exhibiting properties absent in their smaller-scale equivalents. High-aspect-ratio mechanical resonators are crucial for precision sensing, ranging from macroscopic gravitational wave detectors to nanoscale acoustics. Nevertheless, fabrication difficulties and significant computational expenses have restricted the length-to-thickness ratio of these devices, leaving a substantial area in nano-engineering unexplored. We introduce, for the first time, nanomechanical resonators that extend several centimeters in length while maintaining nanometer-scale thickness. We investigate this novel design space using an optimization approach that strategically utilizes rapid millimeter-scale simulations to guide the more computationally demanding centimeter-scale design optimization. The combination of nanofabrication, machine learning-guided design optimization, and precision engineering paves the way for a solid-state approach to room temperature quality factors of 10 billion at kilohertz mechanical frequencies—comparable to the extreme performance of top cryogenic resonators and levitated nanospheres, even under much less stringent temperature and vacuum conditions. Advancing this nanotechnology will necessitate a convergence of new physics insights, innovative structural engineering, and advanced material science.
Presenters
RN
Richard Norte
Associate Prof, Delft University Of Technology
250 visits

Session Participants

Online
Session speakers, moderators & attendees
Head of the Centre of Excellence CEVAS
,
University Of Novi Sad, Faculty Of Technical Sciences, CEVAS
Research Associate
,
The University Of Sheffield
PhD
,
Technische Universität Berlin
PhD
,
Sapienza University Of Rome
Associate Prof
,
Delft University Of Technology
Polytechnic University Of Marche, Ancona, Italy
Professor
,
Politecnico Di Milano
Ms. Panagiota Atzampou
PhD Candidate
,
Delft University Of Technology
Dr. Aditya Ihsan
Telkom University
Dr. Marie Brons
Postdoctoral Researcher/Research Fellow
,
Technical University Of Denmark
43 attendees saved this session

Session Chat

Live Chat
Chat with participants attending this session

Extendend Abstracts

1707377450NewNOLIMASTenoc2024_word_template_updated_2.pdf
On the Design of Metastructures for L...
2
Submitted by Ivana Kovacic
1705609128NF_NNMs_ENOC2024_revised.pdf
Augmenting state-space models with no...
3
Submitted by Tina Dardeno
1707760781Abstract_ENOC.pdf
Hybrid simulation for physics-based a...
4
Submitted by Anouk Zandbergen
1707829917ENOC2024abstract.pdf
Deep learning-based damage identifica...
5
Submitted by Harrish Joseph

Need Help?

Technical Issues?

If you're experiencing playback problems, try adjusting the quality or refreshing the page.

Questions for Speakers?

Use the Q&A tab to submit questions that may be addressed in follow-up sessions.

Upcoming Sessions