Prediction of Shear Strength Using Artificial Neural Networks for Reinforced Concrete Members without Shear Reinforcement

인공신경망을 이용한 전단보강근이 없는 철근콘크리트 보의 전단강도에 대한 예측

  • 정성문 (일리노이 주립대학교 토목공학과) ;
  • 한상을 (인하대학교 건축공학과) ;
  • 김강수 (일리노이 주립대학교 토목공학과)
  • Published : 2005.06.01

Abstract

Due to the complex mechanism and various parameters that affect shear behavior of reinforced concrete (RC) members, models on shear tend to be complex and difficult to utilize for design of structural members, and empirical relationships formulated with limited test data often work lot members having a specific range of influencing parameters on shear. As an alternative approach tot solving this problem, artificial neural networks have been suggested by some researchers. In this paper, artificial neural networks were used to predict shear strengths of RC beams without shear reinforcement. Especially, a large database that consists of shear test results of 398 RC members without shear reinforcement was used for artificial neural network analysis. Three well known approaches for shear strength of RC members, ACI 318-02 shear provision, Zsutiy's equation, and Okamura's relationship, are also evaluated with test results in the shear database and compared with neural network approach. While ACI 318-02 provided inaccurate predictions for RC members without shear reinforcement, the empirical equations by Zsutty and Okamura provided more improved prediction of Shear strength than ACI 318-02. The artificial neural networks, however provided the best prediction of shear strengths of RC beams without shear reinforcement that was closest to test results.

철근콘크리트 부재의 전단거동에 대한 오랜 연구에 의하여 이에 대한 다양한 이론모델들과 제안식들이 존재한다. 그러나 전판거동의 메커니즘이 복잡하고 영향을 미치는 요소들이 많아서 이론모델들은 대부분 매우 복잡한 경향이 있고, 실험에 의한 제안식들은 제한된 범위내의 실험변수에 대해서만 유효한 경우가 많다. 이러한 문제점을 해결할 수 있는 대안의 하나로써 인공신경망이 여러 연구자들에 의하여 제안되어 왔으며, 본 논문에서는 인공신경망을 이용하여 전단보강근이 없는 철근콘크리트 보의 전단강토를 예측하였다 특히, 기존의 전단실험결과를 광범위하게 모아 구축한 데이타베이스를 활용함으로써 넓은 범위의 구조변수들을 포함한 다양한 부재들을 인공신경망의 훈련자료로 이용하였고, 인공신경망에 의한 전단강토 예측 결과를 ACI의 규준식, Zsutty, Okamura의 제안식들과도 비교 분석하였다. ACI의 규준식은 전단보강근이 없는 철근콘크리트 부재에 대해서 매우 부정확한 전단강도를 제공하였으며, Zsutty의 제안식은 ACI의 규준식에 비해 향상된 예측 결과를 보였으나 부재의 크기효과를 반영하지 못하였다. Okamura의 제안식은 주요 변수들의 영향을 비교적 잘 반영하여 상당히 정확하면서도 안정적인 전단강토를 제공하였다 이에 비해 인공신경망은 실험 결과에 가장 근접한 부재의 전단강도를 제공함으로써, 다양한 변수들의 영향을 매우 정확하게 반영할 수 있는 것으로 나타나서 인공신경망이 전단강도와 같이 메커니즘이 복잡하고 영향을 끼치는 변수들이 많은 다른 구조적 거동이나 강도를 예측하는데 매우 적절한 수단을 제공할 수 있음을 보여주었다.

Keywords

References

  1. ASCE-ACI Committee 426(1973) The Shear Strength of Reinforced Concrete Members, Journal of Structural Division, ASCE, 99 (6), pp.1091-1187
  2. ASCE-ACI Committee 445 on Shear and Torsion(1998) Recent Approaches to Shear Design of Structural Concrete, Journal of Structural Engineering, 124(2), pp.1375-1417 https://doi.org/10.1061/(ASCE)0733-9445(1998)124:12(1375)
  3. ACI Committee 318(2002) Building Code Requirements for Structural Concrete (ACI 318-02) and Cotnmentery (ACI 318 R-02), American Concrete Institute, Farmington Hills, p.443
  4. Bazant, Z.P., Kim, J.K.(1984) Size Effect in Shear Failure of Longitudinally Reinforced Beams, ACI Structural Journal, 81 (5), pp.456-468
  5. Collins, M.P., Kuchma, D.A.(1998) Advances in Understanding Shear Performance of Concrete Structures, Progress in Structural Engineering and Materials, 1(4), pp.1-10 https://doi.org/10.1002/pse.2260010103
  6. Ghaboussi, J.(2001) Biologically inspired soft computing methods in structural mechanics and engineering, Structural Engineering and Mechanics, 11(5), pp.485-502 https://doi.org/10.12989/sem.2001.11.5.485
  7. Goh, A.T.C. (1995) Prediction of Ultimate Shear Strength of Deep Beams Using Neural Networks, ACI Structural Journal. 92(1), pp. 28-32
  8. Hertz. J.A ., Krogh. A ., Palmer. R.G.(1991) Introduction to the Theory of Neural Computation, Perseus Publishing
  9. Isenberg. J. (1993) Finite Element Analysis of Reinforced Concrete Structures II, Proc., Int. Workshop, New York
  10. Kani , G.N.J. (1967) How Safe Are Our Large Reinforced Concrete Beams, ACI Journal Proceedings, 64, pp.128-141
  11. Okamura. H .. Higai , T. (1980) Proposed Design Equation for Shear Strength of R.C. Beams without Web Reinforcedment, Proc. of Japan Soc. Civ . Engrg., 300, pp.131-141
  12. Reed. R.D., Marks. R.J.(1999) Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks, MIT Press
  13. Reineck. K.H. (1990) Mechanical Model for the Behaviour of Reinforced Concrete Members in Shear, Ph.D. Thesis, University of Stuttgart
  14. Reineck. K.H., Kuchma , D.A., Kim. K.S., Marx. S. (2003) Shear Database for Reinforced Concrete Members without Shear Reinforcement, ACI Structural Journal, 100 (2), pp.240-249
  15. Riedmiller. M., Braun. H. (1993) A direct adaptive method for faster backpropagation learning: the RPROP algorithm. IEEE International Conference on Neural Networks. San Francisco. IEEE
  16. Sanad. A ., Saka. M.P.(2001) Prediction of Ultimate Shear Strength of Reinforced Concrete Deep Beams Using Neural Networks. Journal of Structural Engineering. 127(7). pp.818-828 https://doi.org/10.1061/(ASCE)0733-9445(2001)127:7(818)
  17. Shioya , T.(1989) Shear Properties of large reinforced concrete member. Special Report of Institute of Technology. Shimizu Corporation. 25
  18. Vecchio. F.J., Collins. M.P. (1986) The Modified Compression Field Theory for Reinforced Concrete Elements Subjected to Shear. Journal of the American Concrete Institute. 83(2). pp.219-231
  19. Vecchio. F.J., Collins. M.P.(1986) Predicting the Resopnse of Reinforced Concrete Beams Subjected to Shear Using the Modified Compression Field Theory. ACI Structural Journal. 85(4). pp.258-268
  20. Zautty , T.C.(1971) Shear Strength Prediction for Separate Categories of Simple Beams Tests. ACI Structural Journal. 68 (2). pp. 138-143