Browse > Article
http://dx.doi.org/10.12673/jant.2019.23.1.84

Machine Learning Based Structural Health Monitoring System using Classification and NCA  

Shin, Changkyo (Department of Aerosapce Engineering, KAIST)
Kwon, Hyunseok (Department of Aerosapce Engineering, KAIST)
Park, Yurim (Department of Aerosapce Engineering, KAIST)
Kim, Chun-Gon (Department of Aerosapce Engineering, KAIST)
Abstract
This is a pilot study of machine learning based structural health monitoring system using flight data of composite aircraft. In this study, the most suitable machine learning algorithm for structural health monitoring was selected and dimensionality reduction method for application on the actual flight data was conducted. For these tasks, impact test on the cantilever beam with added mass, which is the simulation of damage in the aircraft wing structure was conducted and classification model for damage states (damage location and level) was trained. Through vibration test of cantilever beam with fiber bragg grating (FBG) sensor, data of normal and 12 damaged states were acquired, and the most suitable algorithm was selected through comparison between algorithms like tree, discriminant, support vector machine (SVM), kNN, ensemble. Besides, through neighborhood component analysis (NCA) feature selection, dimensionality reduction which is necessary to deal with high dimensional flight data was conducted. As a result, quadratic SVMs performed best with 98.7% for without NCA and 95.9% for with NCA. It is also shown that the application of NCA improved prediction speed, training time, and model memory.
Keywords
Classification; Dimensionality reduction; FBG sensor; Machine learning; Structural health monitoring;
Citations & Related Records
연도 인용수 순위
  • Reference
1 A. Panopoulou, D. Roulias, T. H. Loutas and V. Kostopoulos, "Health monitoring of aerospace structures using fibre Bragg gratings combined with advanced signal processing and pattern recognition techniques," Strain, Vol. 48, No 3, pp. 267-277, May. 2012.   DOI
2 K. Worden and G. Manson, “The application of machine learning to structural health monitoring,” Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 365, No. 1851, pp. 515-537, December. 2006.
3 S. Roy, FK Chang, S. J Lee, P. Pollock, V. Janapati, "A novel machine-learning approach for structural state identification using ultrasonic guided waves," in Proceedings of the 11th International Conference of Structural Safety and Reliability, New York, NY, pp.321-328. June. 2013.
4 H. Azzam, "A practical approach for the indirect prediction of structural fatigue from measured flight parameters," in Proceedings of the Aerotech 95, Birmingham, Octobor. 1995.
5 L. E. Mujica, J. Vehi, W. Staszewski and K. Worden, "Impact damage detection in aircraft composites using knowledge -based reasoning," Structural Health Monitoring, Vol. 7, No. 3, pp. 215-230, September. 2008.   DOI
6 G. Holmes, P. Sartor, S. Reed, P. Southern, K. Worden and E. Cross, "Prediction of landing gear loads using machine learning techniques," Structural Health Monitoring, Vol. 15, No. 5, pp. 568-582, September. 2016.   DOI
7 G. Holmes, A. Thomas, W. Carpener, K. Worden, E. J. Cross, "Data-based classifiers for identification of aircraft landing characteristics," in Proceeding of the 8th European Workshop on Structural Health Monitoring, Bilbao: Spain, July 2016.
8 P. Garre and G. V. Arjun, "Modeling and analysis of a ribs and spars of an airplane wing for bending and shear loads," International Journal For Research in Applied Science and Engineering Technology, Vol. 5, No. 2, pp. 295-315, February. 2017.
9 Mathworks. Choose classifier options. [Internet] Available: https://kr.mathworks.com/help/stats/choose-a-classifier.html