DOI QR코드

DOI QR Code

Tensile strength prediction of corroded steel plates by using machine learning approach

  • Karina, Cindy N.N. (Department of Civil and Environmental Engineering, Ehime University) ;
  • Chun, Pang-jo (Department of Civil and Environmental Engineering, Ehime University) ;
  • Okubo, Kazuaki (Department of Civil and Environmental Engineering, Ehime University)
  • Received : 2016.05.30
  • Accepted : 2017.05.17
  • Published : 2017.08.10

Abstract

Safety service improvement and development of efficient maintenance strategies for corroded steel structures are undeniably essential. Therefore, understanding the influence of damage caused by corrosion on the remaining load-carrying capacities such as tensile strength is required. In this study, artificial neural network (ANN) approach is proposed in order to produce a simple, accurate, and inexpensive method developed by using tensile test results, material properties and finite element method (FEM) results to train the ANN model. Initially in reproducing corroded model process, FEM was used to obtain tensile strength of artificial corroded plates, for which surface is developed by a spatial autocorrelation model. By using the corroded surface data and material properties as input data, with tensile strength as the output data, the ANN model could be trained. The accuracy of the ANN result was then verified by using leave-one-out cross-validation (LOOCV). As a result, it was confirmed that the accuracy of the ANN approach and the final output equation was developed for predicting tensile strength without tensile test results and FEM in further work. Though previous studies have been conducted, the accuracy results are still lower than the proposed ANN approach. Hence, the proposed ANN model now enables us to have a simple, rapid, and inexpensive method to predict residual tensile strength more accurately due to corrosion in steel structures.

Keywords

References

  1. Ahmmad, M.M. and Sumi, Y. (2010), "Strength and Deformability of corroded steel plates under quasi-static tensile load", J. Mar. Sci. Technol., 15(1), 1-15. https://doi.org/10.1007/s00773-009-0066-1
  2. Appuhamy, J.M.R.S., Kaita, T., Ohga, M. and Fujii, K. (2011), "Prediction of residual strength of corroded tensile steel plates", Int. J. Steel Struct., 11(1), 65-79. https://doi.org/10.1007/S13296-011-1006-6
  3. Appuhamy, J.M.R.S., Ohga, M., Kaita, T., Chun, P. and Dissanayake, P.B.R. (2013), "Development of an efficient maintenance strategy for corroded steel bridge infrastructures", J. Bridge Eng., 18(6), 464-475. https://doi.org/10.1061/(ASCE)BE.1943-5592.0000381
  4. Bishop, C.M. (2007), Pattern Recognition and Machine Learning, Springer, Japan.
  5. Bozic, D.Z. (1996), "Optimisation of dissolution using artificial neural network", Farmacevtski Vestnik., 47, 185-186.
  6. Chun, P. and Inoue, J. (2009), "Numerical studies of the effect of residual imperfection on the mechanical behavior of heatcorrected steel plates, and analysis of a further repair method", Steel Compos. Struct., Int. J., 9(3), 209-221. https://doi.org/10.12989/scs.2009.9.3.209
  7. El-Bakyr, M.Y. (2003), "Feed forward neural networks modeling for K-P interactions", Chaos Solution. Fract., 18(3), 995-1000. https://doi.org/10.1016/S0960-0779(03)00068-7
  8. Hastie, T., Tibshirani, R. and Friedman, J. (2014), The Elements of Statistical Learning, Springer, Japan.
  9. Hussain, A.S., Yu, X. and Johnson, R.D. (1991), "Application of neural computing in pharmaceutical product development", Pharm. Res., 8(10), 1248-1252. https://doi.org/10.1023/A:1015843527138
  10. Hussain, A.S., Shivanand, P. and Johnson, R.D. (1994), "Application of neural computing in pharmaceutical product development", Comput. Aid. Formul. Des., Drug Development and Industrial Pharmacy, 20(10), 1739-1752. https://doi.org/10.3109/03639049409038390
  11. Kaita, T., Tagaya, K., Fujii, K., Miyashita, M. and Uenoya, M. (2005), "A simple estimation method of bending strength for corroded plate girder", Collab. Harmoniz. Creative Syst., 1, 89-97.
  12. Kaita, T., Appuhamy, J.M.R.S., Ohga, M. and Fujii, K. (2012), "An enhanced method of predicting effective thickness of corroded steel plates", Steel Compos. Struct., Int. J., 12(5), 379-393. https://doi.org/10.12989/scs.2012.12.5.379
  13. Khedmati, M.R., Nouri, Z.H.M.E. and Roshanali, M.M. (2011), "An effective proposal for strength evaluation of steel plates randomly corroded on both sides under uniaxial compression", Steel Compos. Struct., Int. J., 11(3), 183-205. https://doi.org/10.12989/scs.2011.11.3.183
  14. Muranaka, A., Minata, O. and Fujii, K. (1998), "Estimation of residual strength and surface irregularity of the corroded steel plates", J. Struct. Eng., 44A, 1063-1071. [In Japanese]
  15. Murtoniemi, E., Merkku, P. and Yliruusi, J. (1993), "Comparison of four different Neural network training algorithms in modelling the fluidized bed granulation process", Lab. Microcomp., 12(3), 69-76.
  16. Ohga, M., Appuhammy, J.M.R.S., Kaita, T., Chun, P. and Dissanayake, P.B.R. (2011), "Degradation of tensile strength with the severity of corrosion condition", Proceedings of World Congress on Advances in Structural Engineering and Mechanics (ASEM11+), Seoul, Korea, September, pp. 5280-5297.
  17. Okumura, M., Fujii, K. and Tukai, M. (2001), "Statistical model ofsteel corrosion considering spatial auto-correlation", J. JSCE,672, 109-116. [In Japanese]
  18. Rahgozar, R., Sharifi, Y. and Malekinejad, M. (2010), "Bucklingcapacity of uniformly corroded steel members in terms ofexposure time", Steel Compos. Struct., Int. J., 10(6), 475-487. https://doi.org/10.12989/scs.2010.10.6.475
  19. Richardson, C.J. and Barlow, D.J. (1996), "Neural network computer simulation of aerosols", J. Pharm. Pharmacol., 48(6), 581-591. https://doi.org/10.1111/j.2042-7158.1996.tb05978.x
  20. Sugimoto, I., Kobayashi, Y. and Ichikawa, A. (2006), "Durability evaluation based on buckling characteristics of corroded steel deck girders", Quarterly Rep. of Railway Technical Research Inst. (QR of RTRI), 47(3), 150-155.
  21. Zhang, G.P. (2003), "Time series forecasting using a hybrid ARIMA and neural network model", Neurocomputing, 50, 159-175. https://doi.org/10.1016/S0925-2312(01)00702-0

Cited by

  1. A machine learning approach for predicting the electro-mechanical impedance data of blended RC structures subjected to chloride laden environment vol.31, pp.1, 2022, https://doi.org/10.1088/1361-665x/ac3d6f