CFRP damage identification system based on FBG sensors and ELM method

The identification of the damage state of Carbon fiber-reinforced plastic (CFRP) structure is the necessary information for ensuring the safety of CFRP structure. In this paper, the structural damage identification system using fiber Bragg grating (FBG) sensors and the damage identification method were investigated. FBG sensors were used to detect the structural dynamic response signal, which was generated by an active actuation way. Fourier transform and principal component analysis (PCA) were used to extract the damage characteristic. After that, the structural damage identification model was constructed based on extreme learning machine (ELM), whose input is the damage characteristic and output is the damage state. Finally, the damage identification system was established and verified on a CFRP plate with 160 mm$$\,\times$$×160 mm experiment area. The experimental results showed that the identification accuracy was more than 90 %. This paper provided a reliable method for CFRP structural damage identification.

[1]  D. Liang,et al.  The energy class discrimination of low velocity impacts on composite material structure by Bragg grating sensor technique , 2012 .

[2]  Sergio Oller,et al.  Impact damage identification in composite laminates using vibration testing , 2014 .

[3]  W. Staszewski,et al.  Health monitoring of aerospace composite structures – Active and passive approach , 2009 .

[4]  Joseph Morlier,et al.  Smart monitoring of aeronautical composites plates based on electromechanical impedance measurements and artificial neural networks , 2013 .

[5]  Joël Cugnoni,et al.  Low energy impact damage monitoring of composites using dynamic strain signals from FBG sensors - Part II: Damage identification , 2012 .

[6]  Keith Worden,et al.  On impact damage detection and quantification for CFRP laminates using structural response data only , 2011 .

[7]  Dianhui Wang,et al.  Extreme learning machines: a survey , 2011, Int. J. Mach. Learn. Cybern..

[8]  Jin-Hak Yi,et al.  Sequential damage detection approaches for beams using time-modal features and artificial neural networks , 2009 .

[9]  Theodoros H. Loutas,et al.  Intelligent health monitoring of aerospace composite structures based on dynamic strain measurements , 2012, Expert Syst. Appl..

[10]  P. Capoluongo,et al.  Modal analysis and damage detection by Fiber Bragg grating sensors , 2007 .

[11]  Jin-Hyuk Kim,et al.  Real‐time impact identification algorithm for composite structures using fiber Bragg grating sensors , 2012 .

[12]  In-Gul Kim,et al.  Impact Damage Detection in Composite Laminates Using PVDF and PZT Sensor Signals , 2005 .

[13]  隋青美 Sui Qingmei,et al.  Identification of Impact Location by Using Fiber Bragg Grating Based on Wavelet Transform and Support Vector Classifiers , 2014 .

[14]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[15]  Weilin Huang,et al.  Nonlinear Dimensionality Reduction for Face Recognition , 2009, IDEAL.

[16]  Nobuo Takeda,et al.  Delamination monitoring of laminated composites subjected to low-velocity impact using small-diameter FBG sensors , 2005 .