2-D defect profile reconstruction from ultrasonic guided wave signals based on QGA-kernelized ELM

The reconstruction of defect profiles based on ultrasonic guided waves means the acquisition of defect profiles and parameters from ultrasonic guided wave inspection signals, and it is the key for the inversion of ultrasonic guided waves. A method for the reconstruction of 2-D profiles based on kernelized extreme learning machine (ELM) is presented, and quantum genetic algorithm (QGA) is adopted to optimize the cost parameter C and kernel parameter γ of kernelized ELM. The input data sets of kernelized ELM are defect echo signals, and the output data sets are 2-D profile parameters. The mapping from defect echo signals to 2-D profiles is established. The sample database is achieved by practical experiments and numerical simulations. Then, 2-D profile reconstruction of artificial defects in ultrasonic guided wave testing is implemented with QGA-kernelized ELM. To compare the generalization performance and reconstruction results, another reconstruction model based on LS-SVM is designed simultaneously with the same kernel. Finally, experimental results indicate that proposed method possesses faster speed, lower computational complexity and better generalization performance, and it is a feasible and effective approach to reconstruct 2-D defect profiles.