PREDICTION OF FLOW ACCELERATED CORROSION OF NPP PIPELINE ELEMENTS BY NETWORK SIMULATION METHOD

image_print
DOI https://doi.org/10.15407/pmach2018.03.013
Journal Journal of Mechanical Engineering – Problemy Mashynobuduvannia
Publisher A. Podgorny Institute for Mechanical Engineering Problems
National Academy of Science of Ukraine
ISSN 0131-2928 (Print), 2411-0779 (Online)
Issue Vol. 21, no. 3, 2018 (September)
Pages 13-19
Cited by J. of Mech. Eng., 2018, vol. 21, no. 3, pp. 13-19

 

Authors

Irina Biblik, A. Podgorny Institute of Mechanical Engineering Problems of NASU (2/10, Pozharsky str., Kharkiv, 61046, Ukraine), e-mail: miles@ipmach.kharkov.ua, ORCID: 0000-0002-8650-1134

Konstantin Avramov, A. Podgorny Institute of Mechanical Engineering Problems of NASU (2/10, Pozharsky str., Kharkiv, 61046, Ukraine), e-mail: kvavramov@gmail.com, ORCID: 0000-0002-8740-693X

Roman Rusanov, The Szewalski Institute of Fluid-Flow Machinery Polish Academy of Sciences (14, Fiszera str., Gdańsk 80-231, Poland), e-mail: rrusanov@imp.gda.pl, ORCID: 0000-0003-2930-2574

 

Abstract

Based on a comprehensive approach that uses the computer simulation of the process of destroying structural materials and technology of self-learning neural networks, a methodology has been developed for predicting the rate of flow accelerated corrosion (FAC) of pipeline elements with a single-phase medium of the second circuit of nuclear power plants (NPPs). The neural network model has been implemented in the Delphi Integrated Development Environment. The neural network consists of an input layer containing seven elements and an output layer with two elements. As the input variables of the neural network, the parameters that have the greatest influence on FAC process are chosen. These are the medium temperature, the pipeline internal diameter, the oxygen content in the medium, the  coolant flow velocity, the hydrogen index, the time of monitoring (or the start of operation), and the time for which the prediction is performed. For each of the network input parameters, intervals of possible values were chosen. At that, the factors that affect FAC rate, but not included in the feasible model (chromium, copper and molybdenum content in the pipeline material, amine type) are assumed to be permanent. As the output parameters of the neural network, FAC rate and the variation of the pipeline element wall thickness within the predicted time interval have been selected. As the activation function of the neural network the sigmoid function is used. As a method of training the neural network, the error back propagation method has been chosen, which assumes both a forward and reverse passage through the network layers. As the learning algorithm of the neural network, the one with a teacher has been chosen. As a test sample for the neural network, it is proposed, along with operational control data, to use the results of calculations based on a statistical model created in the framework of a special calculation-experimental method. The application of the developed methodology makes it possible to improve the prediction accuracy of FAC rate without determining all the dependencies between the many factors that influence FAC process. The low errors of the constructed models make it possible to use the results of calculations both to determine the resource characteristics of NPP pipelines and optimize operational control.

 

Keywords: neural networks, computer simulation, flow accelerated corrosion

 

Full text:  Download in PDF

 

References

  1. Naftal, M. M., Baranenko, V. I., & Gulina O. M. (2004). Use of software tools for calculating flow accelerated corrosion of nuclear power plant equipment and pipelines. Thermal Engineering, vol. 61, no. 6, pp. 456–463. https://doi.org/10.1134/S0040601514060081
  2. Baranenko, V. I., Yanchenko, Yu. A., Gulina, O. M., & Dokukin, D. A. (2010). O raschete skorosti erozionno-korrozionnogo iznosa i ostatochnogo resursa truboprovodov AES [Calculation of the rate of erosion-corrosion wear and residual life of NPP pipelines]. Izvestiya vuzov. Yadernaya energetika, no. 2, pp. 55–63 (in Russian).
  3. Mileshkin, M. B. & Biblik, I. V. (2006). Primeneniye spetsialnogo raschetno-eksperimentalnogo metoda dlya otsenki ostatochnogo resursa elementov konstruktsiy po fakticheskomu sostoyaniyu materiala [Application of a special calculation and experimental method for estimating the residual life of structural elements based on the actual state of the material]. Nadezhnost i Dolgovechnost Mashin i Sooruzheniy Reliability and Life of Machines and Installations, iss. 27, pp. 304–310 (in Russian).
  4. Mileshkin, M. B., Biblik, I. V., & Inkulis, V. V. (2009). Otsenka veroyatnosti bezotkaznoy raboty oborudovaniya AES na osnove modelirovaniya izmeneniya stepeni ekspluatatsionnoy povrezhdennosti [Evaluation of the probability of failure-free operation of NPP equipment on the basis of modeling the change in the degree of operational damage]. Nadezhnost i Dolgovechnost Mashin i Sooruzheniy Reliability and Life of Machines and Installations, iss. 32, pp. 105–112 (in Russian).
  5. (2006). RD EO 0571-2006. Normy dopustimykh tolshchin elementov truboprovodov iz uglerodistykh staley atomnykh stantsiy [Norms of admissible thickness of carbon steel pipeline elements of nuclear power plants]. Valid from 2006.11.01. Moscow: OAO Kontsern Rosenergoatom, 44 p. (in Russian).
  6. Baranenko, V. I., Gulina, O. M., & Dokukin, D. A. (2008). Metodologicheskaya osnova prognozirovaniya erozionno-korrozionnogo iznosa oborudovaniya AES metodom neyrosetevogo modelirovaniya [Methodological basis of prediction of erosion-corrosion wear of NPP equipment by the method of neural network modeling]. Izvestiya vuzov. Yadernaya energetika, no. 1, pp. 3–8 (in Russian).
  7. Baranenko, V. I., Getman, A. F., Ovcharov, O. V., & Gusarov, A. Ye. (2006). Ispolzovaniye programmnykh sredstv dlya rascheta korrozii truboprovodov i oborudovaniya energoblokov AES [Use of software for calculation of corrosion of pipelines and equipment of NPP power units]. Available at: www.gidropress.podolsk.ru/files/proceedings/mntk2017/autorun/article19-ru.htm.
  8. Khaykin, S. (2006). Neyronnyye seti [Nuron networks]. Moscow: Izdat. dom Vilyams, 1104 p. (in Russian).

 

Received 07 June 2018

Published 30 September 2018