Ultrasound for improved crack detection

I have a created a modelling tool that can calculate ultrasonic sensitivity of cracks in pipelines, which is 8 times faster than commercial software. The model can simulate the behaviour and characteristics of waves within a pipe wall which are generated when an ultrasonic transmitter is radiating sound towards the pipe wall. These internal waves will be distorted somehow when encountering a crack, so knowing how these waves behave is vital in optimizing sensitivity in crack detection applications.

We built an AI tool to help avoid environmental disasters

Artificial intelligence helps us more and more with decision-making in fields such as medicine, transportation, and information retrieval. In collaboration with Equinor, Norway’s biggest oil and gas company, we have now added another field to the list: Interpreting integrity logs from oil and gas wells. Together, we built an AI-based assistant for Equinor’s log interpreters that they are now using in their daily work.

Uncovering stiff or leaky heart valves

Modern ultrasound scanners combined with technological developments at NTNU may improve diagnostics for dis- eases related to narrow or leaky heart valves. Advanced 3D Doppler and high frame rate imaging makes it possible to visualise cardiac flow and minor movements of the heart’s muscular tissue more precisely, according to PhD Candidates Torvald Espeland and Erik Andreas Rye Berg.

Automating heart monitoring

Heart disease is a major public health issue, and every year, more than 100,000 heart valve operations are performed in the United States alone. With these kinds of numbers, it is more and more urgent to simplify diagnosis and monitoring of heart patients. I/we believe automating the interpretation of ultrasound results is the way forward.