2023-11-05 21:10:00
Using a combination of nuclear technology and machine learning (ML), a team of scientists from the U.S. Department of Energy’s (DOE) Argonne National Laboratory has revealed a significant discovery for maintaining the safety and efficiency of a next-generation type of nuclear reactor, known as a sodium-cooled fast reactor (SFR).
Main lessons
Argonne scientists designed a machine learning system to continuously monitor the SFR cooling system and quickly detect anomalies. The METL facility is a unique experimental facility designed to safely and accurately test materials and components proposed for use in these reactors. The team plans to refine the model to distinguish between true process anomalies and random measurement noise. Combining nuclear technology and machine learning opens up promising prospects for the future of nuclear energy.
The role of sodium-cooled fast reactors
And SFR is a type of nuclear reactor that uses liquid sodium to cool its core and effectively create carbon-free electricity by splitting heavy atoms.
Although not yet in commercial use in the United States, many believe these reactors might transform energy production and help reduce nuclear waste. They do, however, present challenges, such as maintaining the purity of their sodium coolant at high temperatures. This aspect is crucial to prevent corrosion and blockages in the system.
The contribution of machine learning
To address these challenges, Argonne scientists designed a new ML system, which is detailed in a recent article in the revue Energies.
« By harnessing the power of machine learning to continuously monitor and detect anomalies, we advance the state of the art in instrumentation control “, commented Alexander Heifetz, senior nuclear engineer at Argonne and co-author of the article. “ This will create a breakthrough in the efficiency and cost-effectiveness of nuclear energy systems. »
How the ML model works
First, the team created an ML model to continuously monitor the cooling system. The model is equipped to analyze data from 31 sensors of the installation METL (Mechanisms Engineering Test Loop) systems from Argonne that measure variables such as fluid temperatures, pressures and flow rates.
Argonne’s Mechanisms Engineering Test Loop (METL) facility, established in 2010, is a mid-scale liquid metal experimental facility that supplies purified R-grade sodium to various experimental test vessels to test components that must operate in a prototypical advanced reactor environment. Experiments conducted at the METL facility contribute significantly to the development of advanced reactors.
The METL facility is a unique experimental facility designed to safely and accurately test materials and components proposed for use in these reactors. It also trains the engineers and technicians (and now ML models) who might help operate and maintain them.
The Mechanisms Engineering Test Loop facility at Argonne National Laboratory is the largest liquid metals testing facility in the United States. METL tests small and medium-sized components for use in sodium-cooled fast reactors.
A comprehensive system enhanced with ML can facilitate more robust monitoring and prevent anomalies that might disrupt the operation of a real reactor.
Anomaly detection and future improvements
Second, the team demonstrated the model’s ability to quickly and accurately detect operational anomalies. They put this to the test by simulating a loss of coolant type anomaly, which is characterized by a sudden increase in temperature and flow. The model detected the anomaly approximately three minutes following its initiation. This capability highlighted its effectiveness as a security mechanism.
Finally, the research indicates significant improvements for future models. As it stands, the model reports any spike that exceeds a predetermined threshold. However, this method might lead to false alarms due to incidental spikes or sensor errors. Not all spikes are anomalies.
The team plans to refine the model to distinguish between true process anomalies and random measurement noise. This includes the requirement that the signal remains above the threshold value for a certain period of time before it is considered an anomaly. They will also integrate spatial and temporal correlations between sensors in the loss calculation.
Synthetic
The combination of nuclear technology and machine learning opens up promising prospects for the future of nuclear energy. By continuously monitoring and quickly detecting anomalies, we can ensure the reliability and durability of sodium-cooled fast reactors, making nuclear power an even more promising solution for our future energy needs.
Picture gallery
Installation you METL
For a better understanding
What is a sodium-cooled fast reactor (SFR)?
An SFR is a type of nuclear reactor that uses liquid sodium to cool its core and efficiently create carbon-free electricity by splitting heavy atoms.
Why are SFRs not yet used commercially in the United States?
SFRs present challenges, such as maintaining the purity of their sodium coolant at high temperatures, which is crucial to preventing corrosion and blockages in the system.
Argonne scientists designed a new machine learning system that continuously monitors the cooling system and quickly detects anomalies, improving the efficiency and safety of SFRs.
What is the METL installation and what is its role?
The METL facility is a unique experimental facility designed to safely and accurately test materials and components proposed for use in these reactors. It also trains the engineers and technicians (and now the machine learning models) who might help operate and maintain them.
What are the improvements for future machine learning models?
The team plans to refine the model to distinguish between true process anomalies and random measurement noise. This includes the requirement that the signal remains above the threshold value for a certain period of time before it is considered an anomaly. They will also integrate spatial and temporal correlations between sensors in the loss calculation.
[ Rédaction ]
1699219910
#sensors #machine #learning #nuclear #reactor #safety