Defect sizing in guided wave imaging structural health monitoring using convolutional neural networks

Abstract This paper proposes an automatic defect localization and sizing procedure for Structural Health Monitoring based on guided waves imaging. The procedure is applied to an aluminum plate equipped with active piezoelectric sensors. The defect localization and sizing strategy is obtained through to the use of a convolutional neural network trained exclusively on numerical simulations of guided wave signals and post-processed by the delay and sum imaging algorithm. The paper shows the effectiveness of the proposed approach to invert both synthetic and experimental data.