Machine-learning-based approach for post event assessment of damage in a turn-of-the-century building structure

  • Ebrahim Nazarian
  • Todd Taylor
  • Tian Weifeng
  • Farhad Ansari
Original Paper


The work presented in this article describes development of a machine learning (ML)-based platform for condition assessment of building structures in the aftermath of extreme events. The methods employed in the study include support vector machines, neural networks, and Gaussian Naïve Bayes techniques for training of the structural health monitoring model. The ML platform relates the change in stiffness, and strains in various structural components of the system to the intensity and location of damage. Evaluation of the proposed method was accomplished by using it for the characterization of damage in a turn-of-the-century, six-story building with timber frames and masonry walls. The building was damaged due to differential settlement of its foundation. Application of the proposed method in the building required load testing of selected structural elements, and use of the strains acquired from the field tests as input to the ML model.


Historic buildings Structural health monitoring Damage assessment Neural networks Machine learning Foundation settlement Support vector machines Gaussian Naïve Bayes 


  1. 1.
    Karbhari V, Ansari F (2009) Structural health monitoring of civil infrastructure systems Cambridge. Woodhead Publishing Limited, LondonCrossRefGoogle Scholar
  2. 2.
    Compan V, Pachon P, Camara M, Lourenco PB, Saez A (2017) Structural safety assessment of geometrically complex masonry vaults by non-linear analysis. The Chapel of the Wurzburg Residence (Germany). Eng Struct 140:1–13CrossRefGoogle Scholar
  3. 3.
    Frizzarin M, Feng MQ, Franchetti P, Soyoz S, Modena C (2010) Damage detection based on damping analysis of ambient vibration data. Struct Control Health Monit 17(4):368–385Google Scholar
  4. 4.
    Haji Agha Mohammad Zarbaf SE, Norouzi M, Allemang RJ, Hunt VJ, Helmicki A (2017) Stay cable tension estimation of cable-stayed bridges using genetic algorithm and particle swarm optimization. J Bridge Eng 22(10):05017008CrossRefGoogle Scholar
  5. 5.
    Haji Agha Mohammad Zarbaf SE, Norouzi M, Allemang RJ, Hunt VJ, Helmicki A, Nims DK (2017) Stay force estimation in cable-stayed bridges using stochastic subspace identification methods. J Bridge Eng 22(9):04017055CrossRefGoogle Scholar
  6. 6.
    Karapetrou S, Manakou M, Bindi D, Petrovic B, Pitilakis K (2016) ”Time-building specific” seismic vulnerability assessment of a hospital RC building using field monitoring data. Eng Struct 112:114–132CrossRefGoogle Scholar
  7. 7.
    Mostavi A (2017) Wavelet based harmonics decomposition of ultrasonic signal in assessment of plastic strain in aluminum. Measurement 106:66–78CrossRefGoogle Scholar
  8. 8.
    Saboonchi H, Ozevin D, Kabir M (2016) MEMS sensor fusion: acoustic emission and strain. Sens Actuators A 247:566–578CrossRefGoogle Scholar
  9. 9.
    Ni YC, Lu XL, Lu WS (2016) Field dynamic test and Bayesian modal identification of a special structure—the palms together Dagoba. Struct Control Health Monit 23(5):838–856CrossRefGoogle Scholar
  10. 10.
    Ren WX, De Roeck G (2002) Structural damage identification using modal data. I. Simulation verification. J Struct Eng A 128(1):87–95CrossRefGoogle Scholar
  11. 11.
    Ren WX, De Roeck G (2002) Structural damage identification using modal data. II. Test verification. J Struct Eng A 128(1):96–104CrossRefGoogle Scholar
  12. 12.
    Gaviria CA, Montejo LA (2016) Output-only identification of the modal and physical properties of structures using free vibration response. Earthq Eng Eng Vib 15(3):575–589CrossRefGoogle Scholar
  13. 13.
    Saisi A, Gentile C, Guidobaldi M (2015) Post-earthquake continuous dynamic monitoring of the Gabbia Tower in Mantua, Italy. Constr Build Mater 81:101–112CrossRefGoogle Scholar
  14. 14.
    Qian YY, Mita A (2008) Acceleration-based damage indicators for building structures using neural network emulators. Struct Control Health Monit 15(6):901–920CrossRefGoogle Scholar
  15. 15.
    Hung SL, Huang CS, Wen CM, Hsu YC (2003) Nonparametric identification of a building structure from experimental data using wavelet neural network. Comput Aided Civ Infrastruct Eng 18(5):356–368CrossRefGoogle Scholar
  16. 16.
    Cha YJ, Buyukozturk O (2015) Structural damage detection using modal strain energy and hybrid multiobjective optimization. Comput Aided Civ Infrastruct Eng 30(5):347–358CrossRefGoogle Scholar
  17. 17.
    Hippert HS, Pedreira CE, Souza RC (2001) Neural networks for short-term load forecasting: a review and evaluation. IEEE Trans Power Syst 16(1):44–55CrossRefGoogle Scholar
  18. 18.
    Hagan MT, Menhaj MB (1994) Training feedforward networks with the Marquardt algorithm. IEEE Trans Neural Netw 5(6):989–993CrossRefGoogle Scholar
  19. 19.
    Furey TS, Cristianini N, Duffy N, Bednarski DW, Schummer M, Haussler D (2000) Support vector machine classification and validation of cancer tissue samples using microarray expression data. Bioinformatics 16(10):906–914CrossRefGoogle Scholar
  20. 20.
    Tong S, Koller D (2001) Support vector machine active learning with applications to text classification. J Mach Learn Res 2(Nov):45–66Google Scholar
  21. 21.
    Milgram J, Cheriet M, and Sabourin R (2006) “One Against One” or “One Against All”: which one is better for handwriting recognition with SVMs. In: Tenth international workshop on frontiers in handwriting recognition, SuvisoftGoogle Scholar
  22. 22.
    John GH, Langley P (1995) Estimating continuous distributions in Bayesian classifiers. In: Proceedings of the Eleventh conference on Uncertainty in artificial intelligence, Morgan Kaufmann Publishers Inc., pp 338–345Google Scholar
  23. 23.
    Ansari F (2007) Practical implementation of optical fiber sensors in civil structural health monitoring. J Intell Mater Syst Struct 18(8):879–889CrossRefGoogle Scholar
  24. 24.
    Meng D, Ansari F (2013) Damped fiber optic low-frequency tiltmeter for real-time monitoring of structural displacements. Measur Sci Technol 24(12):125106CrossRefGoogle Scholar
  25. 25.
    Nazarian E, Ansari F, Azari H (2015) Recursive optimization method for monitoring of tension loss in cables of cable-stayed bridges. J Intell Mater Syst Struct 27(15):2091–2101CrossRefGoogle Scholar
  26. 26.
    Nazarian E, Ansari F, Zhang X, Taylor T (2016) Detection of tension loss in cables of cable-stayed bridges by distributed monitoring of bridge deck strains. J Struct Eng 142(6):04016018CrossRefGoogle Scholar
  27. 27.
    Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In Ijcai 14(2):1137–1145Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  • Ebrahim Nazarian
    • 1
  • Todd Taylor
    • 1
  • Tian Weifeng
    • 1
  • Farhad Ansari
    • 1
  1. 1.Christopher B. and Susan S. Burke Professor of Civil Engineering, Smart Sensors and NDT Laboratory, Department of Civil and Materials EngineeringUniversity of Illinois at ChicagoChicagoUSA

Personalised recommendations