Operational diagnostics of main equipment APP

Sharayevskij G.S.,
Shapovalova S.I., PhD (Engin.), Associate Professor
National Technical University of Ukraine "Kyiv Polytechnic Institute", pr. Peremohy, 37, Kyiv, 03056, Ukraine
Language: Russian
Source: The Problems of General Energy, 2009, 2(20):35-39
Section: Study and optimization of the technological objects and systems of the energy sector
UDC: 004.032.26
Published: 26.11.2009


In this work the state of existing automated systems for management of technological processes in atomic power-plant was analyzed, and usage of neurocomputing approach to recognition of spectral implementations of stochastic diagnostic signals was proved, which defines actual technical condition of some APP.
As it is known the essence of the problem consists of that up-to-date NPP monitoring-and-control systems being the part of NPP computer-aided manufacturing control systems (CAMCS) have in their base a deterministic approach to logistic analysis of equipment operating conditions to prevent controlled by them parameters from the falling outside preliminary set safe limits. It is obviously not enough for reliable prevention of damages that could occur in a main equipment of nuclear power units. Really some nuclear power units parameters that aren’t directly controlled by CAMCS, particularly temperature conditions of heat exchanging reactor devices, during operation could significantly exceed permissible values that leads to severe damages of these devices, e.g., heat exchange crisis causes burnout and can embrace the whole nuclear core. To exclude such catastrophic events it would be necessary to measure local temperature of fuel elements (in reactor about 40 000 practically uncontrolled fuel elements are located) with the help of many hundreds of thousands of thermocouples placed on the surface alongside these elements that technologically is impossible. In this connection the problem of diagnosis of abnormal heat exchange regimes could be solved by using not temperature measurements of coolant state at nuclear core inlet as it is now, but on the base of recognition of the character of spectra of dynamic components of certain parameters of reactor (in first turn the signals of dynamic pressure in coolant and signals of neutron flux gauges located in the very nuclear core).

Keywords: intelligent diagnostics, pattern recognition, neural networks.


Full text (PDF)