Machine learning-enabled resolution-lossless tomography for composite structures with a restricted sensing capability

Construction of a precise ultrasound tomographic image is guaranteed only when the sensor network for signal acquisition is of adequate density. On the other hand, machine learning (ML), as represented by artificial neural network and convolutional neural network (CNN), has emerged as a prevalent data-driven technique to pre-dictively model high-degree complexity and abstraction. A new tomographic imaging approach, facilitated by ML and based on algebraic reconstruction technique (ART), is developed to implement in-situ ultrasound to-mography, and monitor the structural health of composites with a restricted sensing capability due to insufficient sensors of the sensor network. The blurry ART images, as the inputs to train a CNN with an encoder-decoder-type architecture, are segmented using convolution and max-pooling to extract defect-modulated image features. The max-unpooling boosts the resolution of ART images with transposed convolution. To validate, a carbon fibre -reinforced polymer laminate is prepared with an implanted piezoresistive sensor network, the sensing capa-bility of which is purposedly restrained. Results demonstrate that the developed approach accurately images artificial anomaly and delamination in the laminate, with inadequate training data from the restricted sensor network for tomographic image construction, and in the meantime it minimizes the false alarm by eliminating image artifacts.

Automated summary

This article introduces a tomographic imaging approach based on machine learning and algebraic reconstruction technique for in-situ ultrasound imaging and structural health monitoring of composite materials. By segmenting and extracting features of blurry ART images, it accurately images artificial anomalies and delaminations, while minimizing false alarms.