An on-line weld inspection method for underwater offshore structure based on an improved deep convolutional network

The acoustic signal analysing is a crucial evaluation method for welding repair of in-service marine structures. However, the complex underwater environment complicates the quality evaluations. In addition, the weak acoustic signal poses challenges for traditional methods during signal processing, such as low signal-to-noise ratio and difficulty in feature extraction. In this paper, an improved deep convolutional network method for online weld inspection of underwater offshore structures is proposed. First, a Variational Mode Decomposition (VMD) algorithm is used to extract weak signals. The raw acoustic signal is denoised, and the effective pulses are extracted. Next, the recurrence and gradient plot methods are applied to extract the pulse features and to generate corresponding images. Finally, a VGG16 deep convolutional network is used to classify image samples and determine weld quality online. Results indicate that the VMD algorithm can process and reduce noise, the recurrence and gradient plot provide quality related image features for the neural network. The VGG16 neural network outperforms the VGG19, RESNET34, and RESNET50 neural networks and can achieve a 97.5% recognition rate. This paper offers some avenues for online identification of weld quality in underwater welding.