Ultrasonic guided wave technology has played a significant role in the field of non-destructive testing as it employs acoustic waves that have advantages of high propagation efficiency and low energy consumption during the inspect process. However, theoretical solutions to guided wave scattering problems using assumptions such as Born approximation, have led to the poor quality of the reconstructed results. Moreover, scattering signals collected from industry sectors are often noised and nonstationary. To address these issues, a novel physics-informed framework (PIF) for quantitative reconstruction of defects using the integration of data-driven method with the guided wave scattering analysis has been proposed in this paper. Based on the geometrical information of defects and initial results obtained by PI-based analysis of defect reconstructions, a deep learning neural network model is built to reveal the physical relationship between defects and the noisy detection signals. This data-driven learning model is then applied to quantitatively assess and characterize defect profiles in structures, improve the accuracy of the analytical model and eliminate the impact of noise pollution in the process of inspection. To demonstrate advantages of the developed PIF for complex defect reconstructions with the capability of denoising, numerical examples including basic defect profiles, a stepped defect, a mixed-type defect have been examined. Results show that PIF has greater accuracy for reconstruction of defects in structures as compared with the analytical method and provides a valuable insight into the development of artificial intelligence-assisted inspection systems with high accuracy and efficiency in the fields of structural integrity and condition monitoring.
|Journal||Applied Mathematics and Mechanics|
|Publication status||Accepted/In press - 12 Aug 2022|