Nuclear Engineering and Technology

  • 제56권10호
  • /
  • Pages.4149-4157
  • /
  • 2024
  • /
  • 1738-5733(pISSN)
  • /
  • 2234-358X(eISSN)
한국원자력학회 (Korean Nuclear Society)
권호 표지
DOI QR코드

DOI QR Code

Estimation of residual stress in dissimilar metals welding using deep fuzzy neural networks with rule-dropout

  • Ji Hun Park (Department of Nuclear Engineering, Chosun University) ;
  • Man Gyun Na (Department of Nuclear Engineering, Chosun University)
  • 투고 : 2024.03.04
  • 심사 : 2024.05.16
  • 발행 : 2024.10.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Welding processes are used to connect several components in nuclear power plants. These welding processes can induce residual stress in welding joints, which has been identified as a significant factor in primary water stress corrosion cracking. Consequently, the assessment of welding residual stress plays a crucial role in determining the structural integrity of welded joints. In this study, a deep fuzzy neural networks (DFNN) with a rule-dropout method, which is an artificial intelligence (AI) method, was used to predict the residual stress of dissimilar metal welding. ABAQUS, a finite element analysis program, was used as the data collection tool to develop the AI model, and 6300 data instances were collected under 150 analysis conditions. A rule-dropout method and genetic algorithm were used to optimize the estimation performance of the DFNN model. DFNN with the rule-dropout model was compared to a deep neural network method, known as a general deep learning method, to evaluate the estimation performance of DFNN. In addition, a fuzzy neural network method and a cascaded support vector regression method conducted in previous studies were compared. Consequently, the estimation performance of the DFNN with the rule-dropout model was better than those of the comparison methods. The welding residual stress estimation results of this study are expected to contribute to the evaluation of the structural integrity of welded joints.

키워드

과제정보

This study was supported by a research fund from the Chosun University (2020).

참고문헌

  1. N.S.M. Nasir, M.K.A.A. Razab, S. Mamat, M. Iqbal, Review on welding residual stress, ARPN J. Eng. Appl. Sci. 11 (9) (2016) 6166-6175.
  2. K.S. Lee, W. Kim, J.G. Lee, Assessment of possibility of primary water stress corrosion cracking occurrence based on residual stress analysis in pressurizer safety nozzle of nuclear power plant, Nucl. Eng. Technol. 44 (3) (2012) 343-354.
  3. P. Scott, M.C. Meunier, Materials Reliability Program: Review of Stress Corrosion Cracking of Alloys 182 and 82 in PWR Primary Water Service (MRP-220), EPRI Palo Alto CA 1015427, 2007.
  4. N. Gubeljak, J. Predan, R. Pippan, M. Oblak, Effect of residual stresses on the fatigue crack propagation in welded joints, J. ASTM Int. (JAI) 2 (3) (2005) 281-298.
  5. J.S. Kim, Investigation on the studies for welding residual stresses in nuclear components, Trans. KPVP 12 (1) (2016) 30-40.
  6. M.G. Na, J.W. Kim, D.H. Lim, Prediction of residual stress for dissimilar metals welding at nuclear power plants using fuzzy neural network models, Nucl. Eng. Technol. 39 (4) (2007) 337-348.
  7. Y.D. Koo, K.H. Yoo, M.G. Na, Estimation of residual stress in welding of dissimilar metals at nuclear power plants using cascaded support vector regression, Nucl. Eng. Technol. 49 (4) (2017) 817-824.
  8. T. Takagi, M. Sugeno, Fuzzy identification of systems and its applications to modeling and control, IEEE Trans. Systems, Man, Cybern SMC-15 (1) (1985) 116-132.
  9. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: a simple way to prevent neural networks from overfitting, J. Mach. Learn. Res. 15 (1) (2014) 1929-1958.
  10. H.S. Jo, Y.D. Koo, J.H. Park, S.W. Oh, C.H. Kim, M.G. Na, Prediction of golden time for recovering SISs using deep fuzzy neural networks with rule-dropout, Nucl. Eng. Technol. 53 (12) (2021) 4014-4021.
  11. J. McCall, Genetic algorithms for modelling and optimization, J. Comput. Appl. Math. 184 (1) (2005) 205-222.
  12. W. Liu, Z. Wang, X. Liu, N. Zeng, Y. Liu, F.E. Alsaadi, A survey of deep neural network architectures and their applications, Neurocomputing 234 (2017) 11-26.
  13. P.J. Werbos, Backpropagation through time: what it does and how to do it, Proc. IEEE 78 (10) (1990) 1550-1560.
  14. P. Liashchynskyi, P. Liashchynskyi, Grid Search, Random Search, Genetic Algorithm: a Big Comparison for NAS, 2019 arXiv preprint arXiv:1912.06059.
  15. S.L. Chiu, Fuzzy model identification based on cluster estimation, J. Intell. Fuzzy Syst. 2 (3) (1994) 267-278.