Researchers from the University of Michigan have developed a new machine vision system for testing materials and parts for nuclear reactors.
The system uses microscopy data to detect and quantify radiation-induced problems such as defects and swelling. The researchers hope the system could speed up the development of components for advanced nuclear reactors, which may play a critical role in reducing greenhouse gas emissions.
“We believe we are the first research team to ever demonstrate real-time image-based detection and quantification of radiation damage on the nanometre length scale in the world,” said Professor Kevin Field, a Michigan nuclear engineer and VP of machine vision start-up Theia Scientific.
The new technology was tested at the Michigan Ion Beam Laboratory. By directing beams of ions at material samples, the lab can quickly emulate the damage sustained after years or decades of use in a nuclear reactor. The team used an ion beam of the noble gas krypton to test a radiation-tolerant sample of iron, chromium, and aluminium of interest for use in fission and fusion reactors.
“If radiation exposure makes your metal like Swiss cheese instead of a good Wisconsin cheddar, you would know it’s not going to have structural integrity,” said Field.
The krypton ions create radiation defects in the sample; in this case, a plane of missing or extra atoms sandwiched between two ordinary crystal lattice planes. They appear as black dots in the electron microscope images. The lab is able to observe the development of these defects with an electron microscope, which runs during the irradiation process, producing a video.
“Previously, we would record the whole video for the irradiation experiments and then characterise just a few frames,” said Dr Priyam Patki, who ran the experiment with Christopher Field, president of Theia Scientific. “But now, with the help of this technique, we are able to do it for each and every frame, giving us an insight into the dynamic behaviour of the defects in real time.”
To assess radiation-induced defects, researchers would typically download the video and count every defect in selected frames. With the hundreds, or even thousands, of images or video frames created by modern microscopes, much of the detailed information would be lost, as counting the defects manually in every frame is so laborious.
Instead, the team used Theia Scientific’s software to detect and quantify the radiation-induced defects instantaneously during the experiment. The software displays the results in graphics overlaid on the electron microscope imagery, which label the defects (giving size, number, location and density) and summarise this information as a measure of structural integrity.
“The real-time assessment of structural integrity allows us to stop early if a material is performing badly and cuts out any extensive human-based quantification,” said Field. “We believe that our process reduces the time from idea to conclusion by nearly 80 times.”
Theia’s software uses a convolutional neural network, a type of artificial neural network often used for interpreting images, to analyse the video frames. The neural network achieved high speed and robust interpretation across samples of varying quality, and this in turn enabled the leap from manual interpretation to real-time machine vision.
It is hoped that the interpretation technique could be adapted for other types of image-based microscopy. Field commented: “We see clear pathways to accelerate discoveries in the energy, transportation and biomedical sectors.”
Sign up to the E&T News e-mail to get great stories like this delivered to your inbox every day.