Nuclear reactor power levels can be monitored using seismic and acoustic data

According to a new study published in Seismological research letters.
By applying several machine learning models to the data, researchers at Oak Ridge National Laboratory were also able to predict when the reactor transitioned from on to off and estimate its power levels, with an accuracy of about 66 %.
The findings provide another tool for the international community to cooperatively verify and monitor nuclear reactor operations in a minimally invasive way, said study lead author Chengping Chai, a geophysicist at Oak Ridge. “Nuclear reactors can be used for both benign and nefarious activities. Therefore, verifying that a nuclear reactor operates as claimed is of interest to the nuclear nonproliferation community.”
Although seismic and acoustic data have long been used to monitor earthquakes and the structural properties of infrastructure such as buildings and bridges, some researchers are now using this data to take a closer look at motion associated with industrial processes. In this case, Chai and his colleagues deployed seismic and acoustic sensors around the Oak Ridge High Flux Isotope Reactor, a research reactor used to produce neutrons for studies in physics, chemistry, biology, engineering and life science. materials.
The power state of the reactor is a thermal process, with a cooling tower that dissipates the heat. “We found that seismo-acoustic sensors can record the mechanical signatures of vibrating equipment such as cooling tower fans and pumps with sufficient accuracy to illuminate operational questions,” Chai said.
The researchers then compared a number of machine learning algorithms to find out which were best at estimating the reactor power state from specific seismo-acoustic signals. The algorithms were trained with seismic data only, acoustic data only, and both types of data collected over a year. The combined data produced the best results, they found.
“Seismo-acoustic signals associated with different power levels show complicated patterns that are difficult to analyze with traditional techniques,” Chai explained. “Machine learning approaches are able to infer the complex relationship between different reactor systems and their seismo-acoustic footprint and use it to predict power levels.”
Chai and his colleagues detected some interesting signals during their study, including vibrations from a noisy pump during reactor shutdown, which disappeared when the pump was replaced.
Chai said it is a long-term and challenging goal to associate seismic and acoustic signatures with different industrial activities and equipment. For the High Flux Isotope Reactor, preliminary research shows that fans and pumps have different seismo-acoustic footprints and that different fan speeds have their own unique signatures.
“Some normal but less frequent activities such as annual or incidental maintenance should be distinguished in seismic and acoustic data,” Chai said. To better understand how these signatures relate to specific operations, “we need to study both the seismic and acoustic signatures of instruments and the background noise in various industrial facilities.”
Source of the story:
Material provided by Seismological Society of America. Note: Content may be edited for style and length.