Ship pipeline defect detection method based on deep learning and transfer fusion of ultrasonic guided wave signals

Ultrasonic guided waves (UGW) hold great promise for structural health monitoring (SHM) of pipeline structures. However, the inherent complexity of pipeline defect features within the UGW makes the intuitive and accurate identification of defects based only on UGW signals challenging. In addition, the existing neural network-based UGW signal recognition methods require a large number of defect waveform samples, which limits their applicability. This study proposes a signal recognition method based on deep learning and sample transfer fusion for the identification of UGW signals in ship pipelines, allowing to accurately detect their potential defects. A time–frequency imaging algorithm for ship pipeline UGW signals is first introduced using the continuous wavelet transform (CWT) to capture their time–frequency characteristics. Leveraging transfer learning, UGW signal samples from various operational scenarios onshore oil pipelines are then fused to pre-train the GoogLeNet convolutional neural network (CNN) model. Finally, the pre-trained GoogLeNet model is fine-tuned with ship pipeline UGW signal samples, which allows to accurately detect the underlying defects. The experimental results demonstrate that the proposed method significantly increases the classification accuracy of ship pipeline defects compared with non-transfer learning methods and time-domain imaging. More precisely, the accuracy increases from 63.3% to 97.3%. Furthermore, the obtained results show that the proposed method has high robustness.