Detection of overlapping ultrasonic echoes with deep neural networks

Ultrasonic Pulse-Echo techniques have a significant role in monitoring the integrity of layered structures and adhesive joints along their service life. However, when acoustically measuring thin layers, the resulting echoes from two successive interfaces overlap in time, limiting the resolution that can be resolved using conventional pulse-echo techniques. Deep convolutional networks have arisen as a promising framework, providing state-of-the-art performance for various signal processing tasks. In this paper, we explore the applicability of deep networks for detection of overlapping ultrasonic echoes. The network is shown to outperform traditional algorithms in simulations for a significant range of echo overlaps, echo pattern variance and noise levels. In addition, experiments on two physical phantoms are conducted, demonstrating superiority of the network over traditional methods for layer thickness estimation. •Ultrasonic overlapping echoes are separated using US-CNN, a deep learning framework.•US-CNN is a fully convolutional network trained on simulation.•Simulation is generated based on knowledge of the signal physical model.•US-CNN outperformes competition in simulation for various conditions and edge cases.•Its superiority is shown for layers thickness estimation of two physical phantoms.