Abstract
Structural health monitoring (SHM) program has been widely applied for damage assessment or monitoring the performances and the reliabilities of structures. Usually, structural damage is assessed by discriminating abnormal change from normal change in the structural dynamic behavior. This paper takes the SHM data from a real bridge as a study example and recognizes the trains which daily cross this bridge. The main aim of the current work is to improve the accuracy of structural damage detection. In this paper, symbolic data analysis (SDA) is introduced to extract hidden patterns from raw data, and principal component analysis (PCA) is performed to extract the most important properties of the signals and eliminate the influence of noise. A new representative is proposed in this paper and the recognition results obtained by the clustering algorithms with different representatives are compared. The results show that the new representative is robust to recognize the trains, and PCA is very useful to extract the properties of the signals as well as to reduce the influence of noise.
Similar content being viewed by others
References
Seo J, Phares B, Lu P, Wipf T, Dahlberg J (2013) Bridge rating protocol using ambient trucks through structural health monitoring system. Eng Struct 46:569–580
Lorenzoni F, Casarin F, Caldon M, Islami K, Modena C (2016) Uncertainty quantification in structural health monitoring: applications on cultural heritage buildings. Mech Syst Signal Process 66–67:268–281
Ben BS, Yang SH, Ratnam C, Ben BA (2013) Ultrasonic based structural damage detection using combined finite element and model lamb wave propagation parameters in composite materials. Int J Adv Manuf Technol 67(5):1847–1856
Cury A, Crémona C, Diday E (2010) Application of symbolic data analysis for structural modification assessment. Eng Struct 32(3):762–775
Orcesi AD, Cury A, Cremona C, Dieleman L (2011) Long-term structural health monitoring of a steel road-rail bridge based on symbolic data analysis. Paper presented at the The World Congress on Railway Research, Lille, France
Cremona C (2001) Optimal extrapolation of traffic load effects. Struct Saf 23(1):31–46
Jain AK, Murty MN, Flynn PJ (1999) Data clustering: a review. ACM Comput Surv 31(3):264–323
Adibi MA, Shahrabi J (2014) A clustering-based modified variable neighborhood search algorithm for a dynamic job shop scheduling problem. Int J Adv Manuf Technol 70(9):1955–1961
Malerba D, Esposito F, Monopoli M (2002) Comparing dissimilarity measures for probabilistic symbolic objects. Data mining III, series management information systems 6:31–34
Billard L, Diday E (2006) Symbolic data analysis: conceptual statistics and data mining. John Wiley & Sons Ltd.
Diday E, Noirhomme-Fraiture M (2008) Symbolic data analysis and the SODAS software. WILEY
Dunn JC (1973) A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters. Journal of Cybernetics 3(3):32–57
Azeez MFA, Vakakis AF (2001) Proper orthogonal decomposition (POD) of a class of vibroimpact oscillations. J Sound Vib 240(5):859–889
Marcondes Filho D, Sant’Anna AMO (2016) Principal component regression-based control charts for monitoring count data. Int J Adv Manuf Technol 85(5):1565–1574
Yan AM, Kerschen G, De Boe P, Golinval JC (2005) Structural damage diagnosis under varying environmental conditions—part I: a linear analysis. Mech Syst Signal Process 19(4):847–864
Hua XG, Ni YQ, Ko JM, Asce F, Wong KY (2007) Modeling of temperature–frequency correlation using combined principal component analysis and support vector regression technique. J Comput Civ Eng 21(2):122–135
Yan AM, Kerschen G, De Boe P, Golinval JC (2005) Structural damage diagnosis under varying environmental conditions—part II: local PCA for non-linear cases. Mech Syst Signal Process 19(4):865–880
Davey E, Barratt A, Irwig L, Chan SF, Macaskill P, Mannes P, Saville AM (2006) Effect of study design and quality on unsatisfactory rates, cytology classifications, and accuracy in liquid-based versus conventional cervical cytology: a systematic review. Lancet 367(9505):122–132
Fuxman A, Kannan A, Goldberg AB, Agrawal R, Tsaparas P, Shafer JC (2009) Improving classification accuracy using automatically extracted training data. Paper presented at the KDD '09 Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, Paris, France
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Guo, W., Zhao, H., Gao, X. et al. An efficient representative for object recognition in structural health monitoring. Int J Adv Manuf Technol 94, 3239–3250 (2018). https://doi.org/10.1007/s00170-016-9309-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-016-9309-6