Review of physical models of viscoelastic dampers and prospects for the application of Artificial Intelligence in their design

D.E. Artemenko


 

UDK 62-752.2:004.8

https://doi.org/10.56408/2412-8627.2026.38.70.003


Download the article (RUS)

 

Link to quote


Artemenko, D.E. Review of physical models of viscoelastic dampers and prospects for the application of Artificial Intelligence in their design / D.E. Artemenko // Noise Theory and Practice. – 2026. – Vol. 12, No. 3 (46). – P. 29-46. – DOI: 10.56408/2412-8627.2026.38.70.003

 

Keywords


viscoelastic damper, Poynting-Thomson model, artificial intelligence, physics‑informed neural networks (PINN), parameter identification

 

Abstract


The article discusses modern concepts of viscoelastic damping devices and the analysis of possibilities for using artificial intelligence methods to select their parameters in the process of their design. The main types of dampers by energy dissipation mechanisms (viscous, hysteresis, structural, friction) are considered, their classification by control methods and key technical characteristics are given. The focus is on mathematical models of viscoelastic materials – from the simplest models of Maxwell, Kelvin-Voigt, Poynting-Thompson, to generalized and models with fractional derivatives. The limitations of traditional methods caused by the difficulty of identifying the parameters of computational and nonlinear models are shown. Proposed a two-stage methodology for using artificial intelligence, based on the use of convolutional neural networks for selecting material and physically-informed neural networks for identifying parameters and synthesizing the structure of the damper model. The main problems are identified in the insufficient number and quality of datasets, “reality gap”, the complexity of learning physically informed neural networks and the interpretability of results, as well as possible ways to solve them.

 

The authors of the article


D.E. Artemenko
Baltic State Technical University "VOENMEH", Saint Petersburg, Russia

 

References


ГОСТ Р 55184-2012. Демпферы гидравлические железнодорожного подвижного состава. Общие технические условия / утв. приказом Федерального агентства по техническому регулированию и метрологии от 26.11.2012 № 1163-ст. / разработан Открытым акционерным обществом «Научный и конструкторско-технологический институт подвижного состава» (ОАО «ВНИКТИ») – III, 11 c.; 29 см. – Текст: непосредственный.

 

ГОСТ 17053.1-80. Амортизаторы корабельные АКСС-М. Технические условия [Текст] : государственный стандарт Союза ССР / утверждён Постановлением Госстандарта СССР от 30 мая 1980 г. № 2446. – Москва: Издательство стандартов, 1980. – 18 с.

 

ОСТ 1 03612-72. Демпферы. Типы и основные параметры, технические требования [Текст]: отраслевой стандарт. – 1972. – 9 с.

 

Иванов, Николай Игоревич. Инженерная акустика. Теория и практика борьбы с шумом: учебник / Балтийский государственный технический университет "ВОЕНМЕХ" им. Д.Ф. Устинова. - 5. - Москва: Издательская группа "Логос", 2020. - 432 с. - ISBN 978-5-98704-659-3 : Б. ц.

 

EN 15129:2010. Anti-seismic devices [Text]: European Standard. – Brussels: CEN, 2010. – 171 p.

 

Садек, Ф. Пассивные устройства рассеивания энергии для сейсмостойких зданий / Ф. Садек, Б. Мохраз, А. У. Тейлор, Р. М. Чунг. – Ноябрь 1996. – 66 с. – (NISTIR‑5923; PB97132054).

 

VDI 3830 «Damping of materials and members»: в 5 ч. / VDI-Gesellschaft Produkt und Prozessgestaltung. – URL: https://www.vdi.de/en/home/vdi-standards/details/vdi-3830-blatt-1-damping-of-materials-and-members-classification-and-survey. – Текст: электронный.

 

Baz A. M. Active and passive vibration damping / Amr M. Baz. – Hoboken, NJ, USA: John Wiley & Sons, Inc., 2019. – xxxii, 719 c. – ISBN 978-1-118-48192-9.

 

Патент № 32332 Республика Казахстан, МПК B25J 11/00, F16F 13/00, F16F 15/00. Пространственная амортизационная (демпфирующая) система: № 2015/0711.1: заявл. 14.09.2022; опубл. 21.07.2023 / Бисембаев К., Орынбаева Н. С. ; заявитель и патентообладатель Некоммерческое акционерное общество «Университет имени Шакарима города Семей». – 5 с.: ил. – Текст: непосредственный.

 

Zare Estakhraji S. I. A thorough comparison between measurements and predictions of the amplitude dependent natural frequencies and damping of a bolted structure / S. I. Zare Estakhraji, M. Wall, J. Capito, M. S. Allen // Journal of Sound and Vibration. – 2022. – Vol. 541. – Art. 117397. – DOI: 10.1016/j.jsv.2022.117397.

 

Shirai Y. Energy response of a passive variable friction damper and numerical simulation on the control effects for high rise buildings / Y. Shirai, K. Nakata, A. Toyooka // Structural Control and Health Monitoring. – 2022. – Vol. 29, iss. 12. – Art. e3124. – DOI: 10.1002/stc.3124.

 

Li Q.-Q. Characterization of Dynamic Mechanical Properties of Viscoelastic Damper Based on Physics Constrained Data Driven Approach / Q.-Q. Li, Z.-D. Xu, Y.-R. Dong, Z.-H. He // International Journal of Structural Stability and Dynamics. – 2023. – Vol. 24. – Art. 2450071. – DOI: 10.1142/S0219455424500718.

 

Liu Q. Seismic Optimization of Fluid Viscous Dampers in Cable Stayed Bridges: A Case Study Using Surrogate Models and NSGA II / Q. Liu, Z. Liu, J. Zhao, Y. Lei // Buildings. – 2025. – Vol. 15. – Art. 15(9):1446. – DOI: 10.3390/buildings15091446.

 

Yucesan Y. A. Adjusting a torsional vibration damper model with physics informed neural networks / Y. A. Yucesan, F. A. C. Viana, L. Manin, J. Mahfoud // Mechanical Systems and Signal Processing. – 2021. – Vol. 154. – Art. 107552. – DOI: 10.1016/j.ymssp.2020.107552.

 

Milićević P. Data generation framework for inverse modeling of nonlinear systems in structural dynamics applications / P. Milićević, O. Altay // Acta Mechanica. – 2023. – Vol. 235. – P. 1493–1515. – DOI: 10.1007/s00707-023-03532-3.

 

Hoffmann J. Machine learning in a data limited regime: Augmenting experiments with synthetic data uncovers order in crumpled sheets / J. Hoffmann, Y. Bar Sinai, L. M. Lee, J. Andrejevic // Science Advances. – 2019. – Vol. 5. – Art. eaau6792. – DOI: 10.1126/sciadv.aau6792.

 

Bonfanti A. The Challenges of the Nonlinear Regime for Physics Informed Neural Networks / A. Bonfanti, G. Bruno, C. Cipriani // Advances in Neural Information Processing Systems 37. – 2024. – DOI: 10.52202/079017-1324.

 

Dhurandhar A. Trust Regions for Explanations via Black Box Probabilistic Certification / A. Dhurandhar, S. Haldar, D. Wei, K. Natesan R. // ICML 2024. – 2024. – DOI: 10.48550/arXiv.2402.11168.