Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Pipeline wall thinning rate prediction model based on machine learning

  • Received : 2020.12.16
  • Accepted : 2021.06.27
  • Published : 2021.12.25
Download PDF
⟨ Previous Next ⟩

Abstract

Flow-accelerated corrosion (FAC) of carbon steel piping is a significant problem in nuclear power plants. The basic process of FAC is currently understood relatively well; however, the accuracy of prediction models of the wall-thinning rate under an FAC environment is not reliable. Herein, we propose a methodology to construct pipe wall-thinning rate prediction models using artificial neural networks and a convolutional neural network, which is confined to a straight pipe without geometric changes. Furthermore, a methodology to generate training data is proposed to efficiently train the neural network for the development of a machine learning-based FAC prediction model. Consequently, it is concluded that machine learning can be used to construct pipe wall thinning rate prediction models and optimize the number of training datasets for training the machine learning algorithm. The proposed methodology can be applied to efficiently generate a large dataset from an FAC test to develop a wall thinning rate prediction model for a real situation.

Keywords

Acknowledgement

This work was financially supported by the Korean Nuclear R&D Program organized by the National Research Foundation (NRF) in support of the Ministry of Science and ICT (2017M2A8A4015155 and 2017M2A8A4015158).

References

  1. B. Chexal, J. Horowitz, B. Dooley, P. Millett, C. Wood, R. Jones, M. Bouchacourt, F. Nordmann, P.S. Paul, W. Kastner, Flow-Accelerated Corrosion, EPRI TR-106611-R1, 1998.
  2. T. Satoh, Y. Shao, W.G. Cook, D.H. Lister, S. Uchida, Flow-assisted corrosion of carbon steel under neutral water conditions, Corrosion 63 (2007) 770-780. https://doi.org/10.5006/1.3278426
  3. J.H. Moon, H.H. Chung, K.W. Sung, U.C. Kim, J.S. Rho, Dependency of single-phase FAC of carbon low-alloy steels for NPP system piping on pH, Orifice Distance and Material, Nuclear Engineering and Technology 37 (2004) 357-384.
  4. R.B. Dooley, V.K. Chexal, Flow-accelerated corrosion in pipe wall downstream of orifice for water and air-water bubble flows, Int. J. Pres. Ves. Pip. 77 (2000) 85-90. https://doi.org/10.1016/S0308-0161(99)00087-3
  5. I.S. Woosey, reportAssessment and Avoidance of Erosion-Corrosion Damage in PWR Feedpiperwork, IAEA Report: IWG-RRPC-88-1, Vienna, 19910.
  6. EPRI, CHECKWORKS Computer Program Users Guide, TR-103198-PI, 1997.
  7. W. Kastner, M. Erve, N. Henzel, B. Stellwag, Calculation code for errosion induced wall thinning in piping systems, Nucl. Eng. Des. 119 (1990) 431-438. https://doi.org/10.1016/0029-5493(90)90182-W
  8. S. Trevin, M. Persoz, and T. Knook, Making FAC calculations with BRT-CICEROTM and updating to version 3.0, 17th International Conference on Nuclear Engineering, Vol. 1: Plant Operations, Maintenance, Engineering, Modifications and Life Cycle, Component Reliability and Materials Issues; Nest Generation Systems Brussels Belgium: 81-88.
  9. K. Fujiwara, M. Domae, K. Yoneda, and F. Inada, Effects of Water Chemistry and Fluid Dynamics on Wall Thinning Behavior Part 2 - Evaluation of Influencial Factors by Flow Accelerated Corrosion Tests. CRIEPI-Report: Q09028.
  10. K. Fujiwara, and M. Domae, Effects of Water Chemistry on Wall Thinning Behavior in Single - Phase and Two - Phase Flow, CRIEPI-Report: Q11025.
  11. Y.S. Lee1, S.H. Lee, K.M. Hwang, Cause analysis of flow accelerated corrosion and erosion-corrosion cases in Korea nuclear power plants, Corrosion Science and Technology 15 (5) (2016) 182-188. https://doi.org/10.14773/cst.2016.15.4.182
  12. G. Lee, E.H. Lee, S. Kim, K. Kim, D. Kim, Modeling of flow-accelerated corrosion using machine learning: comparison between random forest and non-linear regression, Corrosion Science and Technology 18 (2) (2019) 61-71.
  13. G. Lee, E.H. Lee, S. Kim, K. Kim, D. Kim, Development of statistical modeling methodology for flow accelerated corrosion: effect of flow rate, water temperature, pH, and Cr content, Korean Society of Pressure Vessels and Piping 12 (2) (2016) 40-49. https://doi.org/10.20466/KPVP.2016.12.2.040
  14. K. M Kim, Y. Choeng, E.H. Lee, J.Y. Lee, S. Oh, D. Kim, Effects of alloys and flow velocity on welded pipeline wall thinning in simulated secondary environment for nuclear power plants, Corrosion Science and Technology 15 (5) (2016) 245-252. https://doi.org/10.14773/cst.2016.15.5.245
  15. S. Moon, S. Han, T. Kang, S. Han, K. Kim, Y. Yu, J. Eom, Impact parameter prediction of a simulated metallic loose Part Using convolutional neural network, Nuclear Engineering and Technology 53 (2021) 1199-1209. https://doi.org/10.1016/j.net.2020.10.009
  16. Y. LeCun, et al., Deep Learning, Nature 521 (7553) (2015) 436-444. https://doi.org/10.1038/nature14539
  17. D.A. Clevert, T. Unterthiner, S. Hochreiter, Fast and accurate deep network learning by exponential linear units (ELUs), ICLR (2016) arXiv:1511.07289.
  18. D.P. Kingma, J. Ba, Adam: a method for stochastic optimization, ICLR (2015).