Structural Health Monitoring using Varied Machine Learning Algorithms

  • Authors

    • B Shanthi
    • Mahalakshmi N
    • Shobana M
    2018-07-20
    https://doi.org/10.14419/ijet.v7i3.12.16503
  • SHM, Machine Learning Algorithms, WEKA.

  • Abstract

    Structural Health Monitoring is essential in today’s world where large amount of money and labour are involved in building a structure. There arises a need to periodically check whether the built structure is strong and flawless, also how long it will be strong and if not how much it is damaged. These information are needed so that the precautions can be made accordingly. Otherwise, it may result in disastrous accidents which may take away even human lives. There are various methods to evaluate a structure. In this paper, we apply various classification algorithms like J48, Naive Bayes and many other classifiers available, to the dataset to check on the accuracy of the prediction determined by all of these classification algorithms and ar-rive at the conclusion of the best possible classifier to say whether a structure is damaged or not.

     

     

  • References

    1. [1] T. Fujiwara, Y. Nakano, J. Mitsugi, and H.Ichikawa, “SDR processing delay estimation applying correlation detection for Structure Health Monitoring using Multi-subcarrier Multiple,†2017.

      [2] N. Mallik, A. S. Wali, and N. Kuri, “Damage location identification through neural network learning from optical fiber signal for structural health monitoring,†Proc. 5th Int. Conf. Mechatronics Control Eng. - ICMCE ’16, pp. 157–161, 2016.

      [3] K. Chintalapudi et al., “Structural damage detection and localization using NETSHM,†2006 5th Int. Conf. Inf. Process. Sens. Networks, pp. 475–482, 2006.

      [4] H. Kaplan and T. Ozkul, “A novel smart fatigue damage sensor for structural health monitoring of critical components of structures,†2016 Int. Conf. Ind. Informatics Comput. Syst. CIICS 2016, 2016.

      [5] P. Sakkos, D. Kotsakos, V. Kalogeraki, D. Gunopulos, and J. Hollmén, “Defining a Mobile Architecture for Structural Health Monitoring,†Proc. 7th Int. Conf. PErvasive Technol. Relat. to Assist. Environ., p. 64:1-- 64:4, 2014.

      [6] Y. Atmojo, K. Anwar, M. G. Andika, and R.N. Wardhani, “Aeroelastic monitoring system: A part of long-span bridge structural health monitoring system,†2017 IEEE Work. Environ. Energy, Struct. Monit. Syst. EESMS 2017 - Proc., 2017.

      [7] S. Paul and W. Yu, “Intelligent Techniques for Bidirectional Structural Health Monitoring,†Proc. 5th Int. Conf. Mechatronics Control Eng. - ICMCE ’16, pp. 52–56, 2016.

      [8] M. Awad, M. AlHamaydeh, and A. F. Mohamed, “Structural damage fault detection using Artificial Neural network profile monitoring,†2017 7th Int. Conf. Model. Simulation, Appl. Optim., pp. 1–6, 2017.

      [9] C. Du, M. Yuan, Q. You, a I. To, and G. Algorithm, “Study on Genetic Algorithm Used in Damage Identification,†2009.

      [10] Sau and I. Bhakta, “Predicting anxiety and depression in elderly patients using machine learning technology,†Healthc. Technol. Lett., vol. 4, pp. 238–243, 2017.

      [11] S. Subba, R. Patange, S. Raja, and B. Aravindu, “Wireless Based Sensor Damage Detection System For Structural Applications,†pp. 312–317, 2016.

      [12] A.Shi and X.Yu, “Structural Damage Assessment Using Artificial Immune Systems and Wavelet Decomposition,†Ijcnn, pp. 242–247, 2017.

      [13] B. Noel, A. Abdaoui, T. Elfouly, M. H. Ahmed, A. Badawy, and M. S. Shehata, “Structural Health Monitoring Using Wireless Sensor Networks: A Comprehensive Survey,†IEEE Commun. Surv. Tutorials, vol. 19, no. 3, pp. 1403–1423, 2017.

      [14] S. Nawaz, X. Xu, D. Rodenas-Herr’aiz, P. Fidler, K. Soga, and C. Mascolo, “Monitoring A Large Construction Site Using Wireless Sensor Networks,†Proc. 6th ACM Work. Real World Wirel. Sens. Networks, pp. 27--30, 2015.

      [15] http:://www.lanl.gov/projects/national-security-education-center/engineering/software/shm-data-seta-and-software.php.

  • Downloads

  • How to Cite

    Shanthi, B., N, M., & M, S. (2018). Structural Health Monitoring using Varied Machine Learning Algorithms. International Journal of Engineering & Technology, 7(3.12), 793-796. https://doi.org/10.14419/ijet.v7i3.12.16503

    Received date: 2018-07-29

    Accepted date: 2018-07-29

    Published date: 2018-07-20