Assessment of the impact of traffic-induced vibrations on buildings using machine learning

openaccess, Vol. 615 (11) 2023 / wtorek, 28 listopada, 2023

(Open Access)

DOI: 10.15199/33.2023.11.02

Jakubczyk-Gałczyńska Anna. 2023. Assessment of the impact of traffic-induced vibrations on buildings using machine learning. Volume 615. Issue 11. Pages 6-9. Article in PDF file

Accepted for publication: 17.08.2023 r.

Traffic induced vibrations may cause plaster cracks, scratches and even collapse of the building. The measurements on real structures are laborious and expensive, and not always justified. The aim is to create a model that can predict the risk of harmful impact of traffic-induced vibrations on the building. After carrying out own measurement studies and analyzing the literature, a model based on Support Vector Machines has been created, taking into account the following factors: building condition, distance of the building from the road edge, soil absorption, type of pavement, condition of the pavement and type of vehicle. The results show that machine learning is a likely tool in forecasting the impact of traffic-induced vibrations on buildings, with high reliability, even over 84%.
  1. Dulińska J, Kawecki J, Kozioł K, Stypuła K, Tatara T. 2014. Oddziaływania Parasejsmiczne Przekazywane na Obiekty Budowlane. Wydawnictwo Politechniki Krakowskiej, Kraków.
  2. Asefa T, Kembłowski M, McKee M, Khalil A. 2006. Multi-time scale stream flow predictions: the support vector machines approach. Journal of Hydrology, 318 (1–4): 7 – 16.
  3.  Çevik A, Kurtoğlu AE, Bilgehan M, Gülşan ME, Albegmprli HM. Support vector machines in structural engineering: a review. Journal of Civil Engineering and Management. 2015; 21 (3): 261 – 281.
  4.  Wabik W. Monitoring system to detect potential dangerous situations. Studia Informatica. 2012; 33 (2B): 497 – 508.
  5.  Firek K, Rusek J, Wodyński A. Wybrane metody eksploracji danych i uczenia maszynowego w analizie stanu uszkodzeń oraz zużycia technicznego zabudowy terenów górniczych. Przegląd Górniczy. 2016; 72 (1): 50 – 55.
  6. JędrzejczykA, Firek K, Rusek J. Convolutional neural network and support vector machine for prediction of damage intensity to multi-storey prefabricated RC buildings. Energies. 2022; 15 (13): 4736.
  7.  Chen WH, Hsu SH, Shen HP. Application of SVM and ANN for intrusion detection. Computers and Operations Research. 2005; 32 (10): 2617 – 2634.
  8.  Cherkassky V, Ma Y. Practical selection of SVM parameters and noise estimation for SVM regression. Neural Networks. 2004; 17 (1): 113 – 126.
  9.  ShaoM,Wang X, Bu Z, Chen X,WangY. Prediction of energy consumption in hotel buildings via support vector machines. Sustainable Cities and Society. 2020; 57: 102128.
  10. Tamilarasi R, Prabu S. Automated building and road classifications from hyperspectral imagery through a fully convolutional network and support vector machine. The Journal of Supercomputing. 2021; 77: 13243 – 13261.
  11. Haykin S. Neural Networks and Machine Learning. Pearson Prentice Hall, New Jersey. 2009; USA.
  12.  Souza CR. Kernel functions for machine learning applications. Creative Commons Attribution–Noncommercial–Share Alike. 2010; 3, 29.
  13.  Cristianini N, Shawe-Taylor J. An Introduction to Support Vector Machines and Other Kernel–based Learning Methods. Cambridge University Press. 2000; UK.
  14. PN-B-02170:2016–12. Ocena szkodliwości drgań przekazywanych przez podłoże na budynki: Evaluation of the harmfulness of building vibrations due to ground motion, Polish Committee for Standardization of Measurement and Quality, 2016 (in Polish).
  15.  Centralna Baza Danych Geologicznych. http://baza.pgi.gov.pl (dostęp online: 27.12.2016).
  16.  Jakubczyk-Gałczyńska A. Predicting the impact of traffic–induced vibrations on buildings using artificial neural networks. Matec Web of Conferences. 2018, 219. 2nd Baltic Conference for Students and Young Researchers. https://doi. org/10.1051/matecconf/201821904004.
  17. Jakubczyk-Gałczyńska A, Kristowski A, Jankowski R., Application of support vector machine for determination of impact of traffic–induced vibrations on buildings. Advances in Intelligent Systems and Computing. 2018; 637: 161 – 167.
  18.  SiemaszkoA, Jakubczyk-GałczyńskaA, Jankowski R. The idea of using Bayesian networks in forecasting impact of traffic-induced vibrations transmitted through the ground on residential buildings. Geosciences; 2019; 9 (8), 339.
  19. Chyży T, Czech KR, Malesza M, Miedziałowski C. 2009. Badania i ocena wpływów drgań drogowych w zespole budynków zabytkowych. Wiadomości Konserwatorskie. 2009; 26: 499 – 509.
  20.  Czech R, Miedziałowski C, Chyży T. Wpływ poprawy stanu drogi na redukcję drgań w zabytkowym kompleksie budynków. Materiały Budowlane. 2015; 6: 105 – 106.
  21. Kawecki J, Stypuła K. Diagnozy a posteriori wpływów drgań drogowych na budynki. XXIV Konferencja Naukowo-Techniczna Awarie Budowlane, Szczecin – Międzyzdroje. 2009; 539 – 546.
  22.  Stypuła K. Wpływ drgań na budynki i ludzi w budynkach – rola badań in situ. 2015 [on–line], [dostęp 17 grudnia 2017 r.]. http://www.map. piib.org.pl/materialy–szkoleniowe.
dr inż. Anna Jakubczyk-Gałczyńska, Politechnika Gdańska, Wydział Inżynierii Lądowej i Środowiska ORCID: 0000-0003-4616-0010

dr inż. Anna Jakubczyk-Gałczyńska, Politechnika Gdańska, Wydział Inżynierii Lądowej i Środowiska ORCID: 0000-0003-4616-0010

annjakub@pg.edu.pl

Full paper:

DOI: 10.15199/33.2023.11.02

Article in PDF file