Steel and Composite Structures

  • 제46권3호
  • /
  • Pages.435-449
  • /
  • 2023
  • /
  • 1229-9367(pISSN)
  • /
  • 1598-6233(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Investigation of random fatigue life prediction based on artificial neural network

  • Jie Xu (Key Laboratory of Earthquake Engineering Simulation and Seismic Resilience of China Earthquake Administration (Tianjin University)) ;
  • Chongyang Liu (Key Laboratory of Earthquake Engineering Simulation and Seismic Resilience of China Earthquake Administration (Tianjin University)) ;
  • Xingzhi Huang (School of Civil Engineering, Tianjin University) ;
  • Yaolei Zhang (School of Civil Engineering, Tianjin University) ;
  • Haibo Zhou (Beijing Construction Engineering Group) ;
  • Hehuan Lian (Beijing Construction Engineering Group)
  • 투고 : 2022.02.08
  • 심사 : 2023.02.01
  • 발행 : 2023.02.10
⟨ 이전 논문 다음 논문 ⟩

초록

Time domain method and frequency domain method are commonly used in the current fatigue life calculation theory. The time domain method has complicated procedures and needs a large amount of calculation, while the frequency domain method has poor applicability to different materials and different spectrum, and improper selection of spectrum model will lead to large errors. Considering that artificial neural network has strong ability of nonlinear mapping and generalization, this paper applied this technique to random fatigue life prediction, and the effect of average stress was taken into account, thereby achieving more accurate prediction result of random fatigue life.

키워드

참고문헌

  1. Artymiak, P., Bukowski, L., Feliks, J., Narberhaus, S. and Zenner, H. (1999), "Determination of S-N curves with the application of artificial neural networks", Fatigue Fracture Eng. Mater. Struct., 22(8), 723-728. https://doi.org/10.1046/j.1460-2695.1999.t01-1-00198.x.
  2. Benasciutti, D. and Tovo, R.(2005), "Spectral methods for lifetime prediction under wide-band stationary random processes", Int. J. Fatigue, 27(8), 867-877. https://doi.org/10.1016/j.ijfatigue.2004.10.007.
  3. Bendat, J.S. and Piersol, A.G.(1966), "Measurement and analysis of random data", Technometrics, 10(4), 869-871. https://doi.org/10.2307/1267469
  4. Bhadeshia, H. (2008), "Neural networks in materials science", Encyclopedia Mater. Sci. Technol., 39(10), 1-5. https://doi.org/10.1016/B978-008043152-9.02201-6.
  5. Chaudhury, G. (1986), "Spectral fatigue of broad-band stress spectrum with one or more peaks", Offshore Technol. Conference, Houston, Texas, USA, May.
  6. Dirlik, T.(1985), Application of Computers in Fatigue Analysis, University of Warwick, Coventry, England, UK.
  7. Du, Y.X., Jun, W., Jian, Y., Lai, Y.F. and Sun, D.H. (2020), "Experimental research on fatigue behavior of prestressed concrete beams under constant-amplitude and variable-amplitude fatigue loading", Construct. Build. Mater., 259, 30. https://doi.org/10.1016/j.conbuildmat.2020.119852.
  8. Durodola, J.F., Li, N., Ramachandra, S. and Thite, A.N. (2017), "A pattern recognition artificial neural network method for random fatigue loading life prediction", Int. J. Fatigue, 99, 55-67. https://doi.org/10.1016/j.ijfatigue.2017.02.003.
  9. Durodola, J.F., Ramachandra, S., Gerguri, S. and Fellows, N. A. (2018), "Artificial neural network for random fatigue loading analysis including the effect of mean stress", Int. J. Fatigue, 111, 321-332. https://doi.org/10.1016/j.ijfatigue.2018.02.007.
  10. Farley, S.J., Durodola, J.F., Fellows, N.A. and Hernandez-Gomez, L.H. (2008), "A neural network approach for locating multiple defects", Appl. Mech. Mater., 13-14, 125-131. https://doi.org/10.4028/www.scientific.net/AMM.13-14.125.
  11. Feng, L., Chen, X.D., Zhang, J.H., Yuan, J.Y. and Dong, W. (2021), "Fatigue behavior and prediction model of self-compacting concrete under constant amplitude load and incremental amplitude load", Int. J. Fatigue, 145(1), 106107. https://doi.org/10.1016/j.ijfatigue.2020.106107.
  12. Feng, L.Y. and Qian, X.D. (2019), "Rapid S-N type life estimation for low cycle fatigue of high-strength steels at a low ambient temperature", Steel Compos. Struct., 33(6), 777-792. https://doi.org/10.12989/scs.2019.33.6.777.
  13. Fu, T.T. and Cebon, D. (2000), "Predicting fatigue lives for bimodal stress spectral densities", Int. J. Fatigue, 22(1), 11-21. https://doi.org/10.1016/S0142-1123(99)00113-9.
  14. Han, Q.H., Li, J., Xu, J., Ye, F. and Lacidogna, G. (2018), "A new frequency domain method for random fatigue life estimation in a wide-band stationary Gaussian random process", Fatigue Fracture Eng. Mater. Struct., 42(10-11), 97-113. https://doi.org/10.1111/ffe.12875.
  15. Han, Q.H., Ye, F. and Xu, J. (2016), "Review of random fatigue research in civil engineering", J. Tianjin Univ. Sci. Technol., 49(S1), 143-151.
  16. Hernandez-Gomez, L.H., Durodola, J.F., Fellows, N.A. and Urriolagoitia-Calderon, G. (2006), "Locating defects using dynamic strain analysis and artificial neural networks", Appl. Mech. Mater., 3-4, 325-330. https://doi.org/10.4028/www.scientific.net/AMM.3-4.325.
  17. Huang, Z.Y., Wang, Q.Y., Wagner, D. and Bathias, C. (2014), "Constitutive model coupled with damage for carbon manganese steel in low cycle fatigue", Steel Compos. Struct., 17(2), 185-198. http://dx.doi.org/10.12989/scs.2014.17.2.185.
  18. Jiao, H., Holloway, D. and Ghazijahani, T.G. (2015), "Fatigue tests of damaged tubes under flexural loading", Steel Compos. Struct., 19(1), 223-236. http://dx.doi.org/10.12989/scs.2015.19.1.223.
  19. Kang, B.H., Kim, H., Kim, Y. and Kim, K.S. (2014), "Development of Fatigue Damage Model of Wide-Band Process by Artificial Neural Network", ASME 2014 33rd International Conference on Ocean, Offshore and Arctic Engineering, San Francisco, California, USA, October.
  20. Kim, K.N., Jung, K.S. and Lee, S.H. (2009), "Prediction on the fatigue life of butt-welded specimens using artificial neural network", Steel Compos. Struct., 9(6), 557-568. http://dx.doi.org/10.12989/scs.2009.9.6.557.
  21. Kim, Y., Kim, H. and Ahn, I.G. (2016), "A study on the fatigue damage model for Gaussian wideband process of two peaks by an artificial neural network", Ocean Eng., 111(JAN.1), 310-322. https://doi.org/10.1016/j.oceaneng.2015.11.008.
  22. Liao, X.W., Wang, Y.Q., Wang, Z.Y., Feng, L.Y. and Shi, Y. J.(2019), "Effect of low temperatures on constant amplitude fatigue properties of Q345qD steel butt-welded joints", Eng. Fail. Anal., 105, 597-609. https://doi.org/10.1016/j.engfailanal.2019.07.006
  23. Matsubara, G. and Hayashida, A. (2021), "Fatigue life prediction for the AISI 4340 steel under multiaxial variable-amplitude loading with respect to the calculated rainflow damage based on the path length", Int. J. Fatigue, 147(3), 106181. https://doi.org/10.1016/j.ijfatigue.2021.106181.
  24. Matsuishi, M. and Endo, T. (1968), "Fatigue of Metals Subjected to Varying Stress", Presented to the Japan Society of Mechanical Engineers, Fukuoka, Japan, January. https://doi.org/10.1103/PhysRevSeriesI.30.62.
  25. Mikheevskiy, S., Glinka, G. and Cordes, T.(2015), "Total life approach for fatigue life estimation of welded structures", Procedia Eng., 101, 177-184. https://doi.org/10.1016/j.proeng.2015.02.023
  26. Pan, H.M. (2016), Research on Fatigue Life of Gearbox of High Speed EMU Based on Three Interval Method, Master Dissertation, Southwest Jiaotong University, Chengdu, China.
  27. Park, J.B., Choung, J. and Kim, K.S. (2014), "A new fatigue prediction model for marine structures subject to wide band stress process", Ocean Eng., 76, 144-151. https://doi.org/10.1016/j.oceaneng.2013.11.002.
  28. Petrucci, G. and Zuccarello, B. (2015), "Fatigue life prediction under wide band random loading", Fatigue Fracture Eng. Mater. Struct., 27(12), 1183-1195. https://doi.org/10.1111/j.1460-2695.2004.00847.x.
  29. Pujol, J.C.F. and Pinto, J.M.A. (2011), "A neural network approach to fatigue life prediction", Int. J. Fatigue, 33(3), 313-322. https://doi.org/10.1016/j.ijfatigue.2010.09.003.
  30. Sakai, S. and Okamura, H. (1994), "On the distribution of rainflow range for Gaussian random process with bimodal PSD", Transact. Japan Soc. Mech. Eng, A, 60(574), 1464-1469. https://doi.org/10.1299/kikaia.60.1464.
  31. Wang, J., Uy, B., Li, D.X. and Song, Y.C. (2020), "Fatigue behaviour of stainless steel bolts in tension and shear under constant-amplitude loading", Int. J. Fatigue, 133, 105401. https://doi.org/10.1016/j.ijfatigue.2019.105401.
  32. Yeter, B., Garbatov, Y. and Soares, C.G. (2015), "Fatigue damage assessment of fixed offshore wind turbine tripod support structures", Eng. Struct., 101, 518-528. https://doi.org/10.1016/j.engstruct.2015.07.038.
  33. Yildirim, H.C., Remes, H. and Nussbaumer, A. (2020), "Fatigue properties of as-welded and post-weld-treated high-strength steel joints: The influence of constant and variable amplitude loads", Int. J. Fatigue, 138, 105687. https://doi.org/10.1016/j.ijfatigue.2020.105687.
  34. Younesian, D., Solhmirzaei, A. and Gachloo, A.(2009), "Fatigue life estimation of MD36 and MD523 bogies based on damage accumulation and random fatigue theory", J. Mech. Sci. Technol., 23(8), 2149-2156. https://doi.org/10.1007/s12206-009-0622-y.
  35. Zhao, W. and Baker, M.J. (1990), "A new stress range distribution model for fatigue analysis under wave loading", Environ. Forces Offshore Struct. Predictions, London, UK, November.