Improve detectability for trustworthiness assessment of concrete structure inspection in ultrasound by AI method

The Norwegian green-tech company Elop has developed an innovative tool and associated digital expert solutions for condition monitoring of concrete structures. The Industrial PhD project will evaluate the effectiveness and repeatability of ELOP's new decision support systems based on expert knowledge and artificial intelligence. Inspection is important for critical infrastructure. ELOP has developed a hand-held ultrasound scanner, Elop Insight, for non-destructive inspection of concrete. The associated digital platform includes effective methods for evaluating and measuring the condition of concrete. The overall purpose is to improve reliability, improve safety, extend service life, minimize life cycle costs and reduce the global environmental footprint of concrete structures. The primary objective of this PhD work will be to introduce reliable data analysis methods based on ultrasonic inspection of concrete. The work will contribute to a new understanding of AI-based tools that make ultrasound inspection more intelligent and less operator-dependent. This project is co-financed by the Norwegian Research Council, and is a collaboration between the University of South-eastern Norway (USN) and the high-tech company ELOP AS.

The first step in the research will be to properly understand the problem at hand, the Elop challenges. This will be followed by a comprehensive literature review, and identification of various metrics to compare against a ground truth in image segmentation in order to generate reliable result. Elop is searching for AI techniques (machine learning, pattern recognition and deep learning) to improve the detection capability of COBRI scanner. The second step will be to investigate a detection model based on deep learning neural networks. To conduct the research, we firstly need to create a very large dataset of various synthetic cases with exactly known ground truth. Namely, a wave simulation tool such as SimSonic is used to simulate realistic cases and measure RF data for each receiver. Using Elop’s beamforming techniques, we can create synthetic images from this RF data. Such images can be validated by comparison with images from the COBRI scanner, where the synthetic and real images are based on the same concrete structure. In the next step, we use supervised learning to train a deep learning-based image segmentation algorithm to reproduce the ground truth from the synthetic images. This leads to acquiring a large dataset of various real cases with known ground truth, measured with the COBRI scanner. Finally, we take the model trained on synthetic data and use transfer learning techniques to re-train it on real data to be able to reproduce ground truth from real images. The methodologies will be published as papers.