DOI QR코드

DOI QR Code

Modeling strength of high-performance concrete using genetic operation trees with pruning techniques

  • Peng, Chien-Hua (Department of Civil Engineering and Engineering Informatics, Chung Hua University) ;
  • Yeh, I-Cheng (Department of Information Management, Chung Hua University) ;
  • Lien, Li-Chuan (Department of Construction Engineering, National Taiwan University of Science and Technology)
  • 투고 : 2008.06.11
  • 심사 : 2009.05.12
  • 발행 : 2009.06.25

초록

Regression analysis (RA) can establish an explicit formula to predict the strength of High-Performance Concrete (HPC); however, the accuracy of the formula is poor. Back-Propagation Networks (BPNs) can establish a highly accurate model to predict the strength of HPC, but cannot generate an explicit formula. Genetic Operation Trees (GOTs) can establish an explicit formula to predict the strength of HPC that achieves a level of accuracy in between the two aforementioned approaches. Although GOT can produce an explicit formula but the formula is often too complicated so that unable to explain the substantial meaning of the formula. This study developed a Backward Pruning Technique (BPT) to simplify the complexity of GOT formula by replacing each variable of the tip node of operation tree with the median of the variable in the training dataset belonging to the node, and then pruning the node with the most accurate test dataset. Such pruning reduces formula complexity while maintaining the accuracy. 404 experimental datasets were used to compare accuracy and complexity of three model building techniques, RA, BPN and GOT. Results show that the pruned GOT can generate simple and accurate formula for predicting the strength of HPC.

키워드

참고문헌

  1. Huang, C.L. (1999), Characteristics and Behaviors of Concrete, Chan's Arch Books, Taipei.
  2. Yeh, I.C. (2004), Applications of Artificial Neural Networks, Scholars books, Taipei.
  3. Yeh, I.C. (1998), "Modeling concrete strength with augment-neuron networks", J. Mater. Civil Eng., 10(4), 263-268. https://doi.org/10.1061/(ASCE)0899-1561(1998)10:4(263)
  4. Yeh, I.C. (1999), "Modeling of strength of high performance concrete using artificial neural networks", Cement Concrete Res., 28(12), 1797-1808.
  5. Kim, J.I., Kim, D.K., Feng, M.Q., and Yazdani, F. (2004), "Application of neural networks for estimation of concrete strength", J. Civil Eng., 16(4), 257-264. https://doi.org/10.1061/(ASCE)0899-1561(2004)16:3(257)
  6. Chen, L. (2003), "A study of applying macroevlutionary genetic programming to concrete strength estimation", ASCE, J. Comput. Civil Eng., 17(4), 290-294. https://doi.org/10.1061/(ASCE)0887-3801(2003)17:4(290)
  7. Chen, L., Tasi, C.S., and Chen, H.M. (2004), "A study of applying grammar evolution to concrete strength estimation", Chung Hua J. Sci. Eng., 2(2), 55-62.
  8. Hamid-Zadeh, N., Jamali, A., Nariman-Zadeh, N., and Akbarzadeh, H. (2007), "Prediction of concrete compressive strength using evolved polynomial neural networks", World Sci. Eng. Acad. Soc. T. Syst., 6(4), 802-807.
  9. Ahmet, O., Murat, P., Erdogan, O., Erdogan, K., Naci C., and Bhatti, M.A. (2006), "Predicting the compressive strength and slump of high strength concrete using neural network", Constr. Build. Mater., 20(9), 769-775. https://doi.org/10.1016/j.conbuildmat.2005.01.054
  10. Lien, L.C., Yeh, I.C., and Cheng, M.Y. (2006), "Modeling strength of high-performance concrete using genetic algorithms and operation tree", J. Tech., 21(1), 41-54.
  11. Davis, L. (1991), Handbook of Genetic Algorithms, Van Nostrand Reinhold, NY.
  12. Goldberg, D.E. (1989), Genetic Algorithms in Search Optimization and Machine Learning, Addison-Wesley Publishing Company, Massachusetts.
  13. Lei, I.J., Chang, S.C., Li, H.W., and Chou, C.M. (2005), An Introduce of GA Toolbox in MATLAB, Xidian University Press.

피인용 문헌

  1. Determining ultimate bearing capacity of shallow foundations using a genetic programming system vol.23, pp.7-8, 2013, https://doi.org/10.1007/s00521-012-1150-8
  2. Modeling the compressive strength of cement mortar nano-composites vol.10, pp.1, 2012, https://doi.org/10.12989/cac.2012.10.1.049
  3. An Optimization System for Concrete Life Cycle Cost and Related CO2 Emissions vol.8, pp.4, 2016, https://doi.org/10.3390/su8040361
  4. Improving semi-empirical equations of ultimate bearing capacity of shallow foundations using soft computing polynomials vol.26, pp.1, 2013, https://doi.org/10.1016/j.engappai.2012.08.014
  5. Improving analytical models of circular concrete columns with genetic programming polynomials vol.14, pp.2, 2013, https://doi.org/10.1007/s10710-012-9176-3
  6. A Fuzzy Adaptive Resonance Theory-Based Model for Mix Proportion Estimation of High-Performance Concrete vol.32, pp.9, 2017, https://doi.org/10.1111/mice.12288
  7. Modeling concrete strength with high-order neural networks vol.27, pp.8, 2016, https://doi.org/10.1007/s00521-015-2017-6
  8. Polynomial modeling of confined compressive strength and strain of circular concrete columns vol.11, pp.6, 2013, https://doi.org/10.12989/cac.2013.11.6.603
  9. Genetic algorithm in mix proportion design of recycled aggregate concrete vol.11, pp.3, 2013, https://doi.org/10.12989/cac.2013.11.3.183
  10. Assessment of the CO2 emission and cost reduction performance of a low-carbon-emission concrete mix design using an optimal mix design system vol.25, 2013, https://doi.org/10.1016/j.rser.2013.05.013
  11. A Study of Applying Genetic Algorithm to Predict Reservoir Water Quality vol.7, pp.2, 2017, https://doi.org/10.7763/IJMO.2017.V7.566
  12. A Study on the GA-Based Design for Recycled Aggregate Concrete vol.284-287, pp.1662-7482, 2013, https://doi.org/10.4028/www.scientific.net/AMM.284-287.1225
  13. An evolutionary system for the prediction of high performance concrete strength based on semantic genetic programming vol.19, pp.6, 2017, https://doi.org/10.12989/cac.2017.19.6.651
  14. Knowledge-based learning for modeling concrete compressive strength using genetic programming vol.23, pp.4, 2009, https://doi.org/10.12989/cac.2019.23.4.255
  15. Application of artificial neural networks for the prediction of the compressive strength of cement-based mortars vol.24, pp.4, 2009, https://doi.org/10.12989/cac.2019.24.4.329
  16. Hybrid Gaussian Process Inference Model for Construction Management Decision Making vol.19, pp.4, 2009, https://doi.org/10.1142/s0219622020500212