Clustering of Acoustic Events in Main Circulation Circuit of WWER 1000/1200 Reactor Facility Caused by Normal Technological Operations

Abstract

The appearance of free, weakly fixed and foreign objects in the main circulation circuit is not ruled out in reactor plants with a pressurized water power reactor. These objects, moving in the coolant flow, can collide with the inner walls of the main circulation circuit, which can lead to equipment damage. Early detection of these objects will minimize damage and improve the safety of NPP operation. The reactor plant is equipped with a system for detecting loose/weakly fixed objects for this purpose. The main problem is a large number of false alarms arising from the registration of noise from the normal operation of the NPP. The paper considers the application of clustering algorithms to signals of the system for detecting loose/weakly fixed objects, which can significantly reduce the number of false alarms as it has been established that signals from the operation of standard equipment are highly repeatable. Then, having “trained” the system on a certain archive of data characterizing the regular functioning of the NPP, we can state that if the newly received signal falls into one of the clusters, then it reflects the normal functioning of the NPP, while the signals do not that fell into any of the clusters may be the result of the appearance of a loose / loosely fixed object, and this situation requires an immediate response from the personnel operating the NPP. This approach makes it possible to reduce the amount of the system for detecting loose/weakly fixed objects output information significantly, reduce the load on the operating personnel, improve the quality of decisions made and, accordingly, increase the safety of operation of the reactor plant as a whole.