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.

No abstract

No abstract

Trouble-free operation of motor-driven valves (MDV) is one of the key factors behind the operating safety of NPPs. As critical components, MDVs are a part of a safety system and a safety-related system. This imposes the highest possible requirements on the MDV reliability. MDVs are the most numerous category of the NPP components. Depending on design, one power unit contains 1500 to 3000 motor-driven valves alone. It follows from an analysis of the NPP failures that many of these are caused by failed motor-driven valves of safety and safety-related systems. The paper presents a description of an automated system for diagnostics of shutoff and control MDVs used in the NPP pipelines. The developed diagnostic algorithms make it possible to take into account the variability of the MDV technical parameters, while taking into account, at the same time, rated restrictions on diagnostic parameters, if any.

Motor operated valves (MOV) are one of the most numerous classes of the nuclear power plant components. An important issue concerned with the MOV diagnostics is the lack of in-process (online) automated control for the MOV technical condition during full power operation of the NPP unit. In this regard, a vital task is that of the MOV diagnostics based on the signals of the current and voltage consumed during MOV ‘opening’ and ‘closing’ operations. The current and voltage signals represent time series measured at regular intervals. The current (and voltage) signals can be received online and contain all necessary information for the online diagnostics of the MOV status. Essentially, the approach allows active power signals to be calculated from the current and voltage signals, and characteristics (‘diagnostic signs’) to be extracted from particular portions (segments) of the active power signals using the values of which MOVs can be diagnosed. The paper deals with the problem of automating the segmentation of active power signals. To accomplish this, an algorithm has been developed based on using a convolutional neural network.