The neural network allows you to make nuclear reactors safer

Engineers from Purdue University (Indiana, USA) are developing a new system that can greatly increase the effectiveness of inspections, the integrity of nuclear reactors through the use of artificial intelligence (AI). In an article published in the journal IEEE Transactions on Industrial Electronics, researchers described the framework for machine learning naïve Bayes - ultra-precise neural network capable of efficiently identify cracks in the reactors on the basis of analysis of individual video frames.

The neural network allows you to make nuclear reactors safer

"Regular inspection of components of nuclear power plants are essential to ensure safe operation," - says Muhammad Jahan, Assistant Professor, School of Civil Engineers named Lyle at Perdue University.

"However, current methods tend to be very time-consuming, tedious, and very often faced with the subjective evaluation, as in the main analysis of the video for the presence of cracks in the reactors is performing technical and people."

Auto Analysis System, developed by Purdue, uses a database, which contains images of about 300 thousand different cracks and other structural characteristics. Efficacy test reactor systems remains high even in the case when the need of inspection of the reactor element is under water, which usually takes place as the water in the reactor is used for cooling. This system reduces the risks to human health. The neural network analyzes each centimeter of each frame in the search for cracks, and then monitors each crack from one frame to another using a data fusion algorithm.

The neural network allows you to make nuclear reactors safer

"The joint processing can improve the adequacy and effectiveness of future decisions made", - continues Jahan, noting that the neural network demonstrates the effectiveness of 98, 3 per cent in the definition of cracks, which is substantially higher than with other, even the most modern methods and approaches.

As the world continues to move towards renewable energy sources, nuclear energy is increasingly becoming not a major, but rather an alternative, although a reliable choice. Non-repudiation of nuclear energy can be explained at least by the fact that solar or wind power plants have a number of limitations and their performance in the first place it depends on the weather operating conditions in which they are located.

One of the main trends in modern physics is the search for the so-called "holy grail" of renewable energy - the possibility of using nuclear fusion to provide all our energy needs. Despite the fact that researchers have achieved very good results in the stabilization and support for nuclear fusion, we are not yet ready to rely on this source of energy. Therefore, currently the only available and safest way of using nuclear energy is still the nuclear fission method of further improving the safety and efficiency of which are working many researchers from around the world. For example, experts observe the progress of the so-called molten-salt reactors, where the basis coolant is a mixture of molten salts, which can operate at high temperatures, while remaining at a low pressure, so that the mechanical stresses are reduced and increased safety and durability.