Modeling of Reinforcement in Concrete Beams Using Machine Learning Tools

Authors: Yogesh Aggarwal

Abstract:

The paper discusses the results obtained to predict reinforcement in singly reinforced beam using Neural Net (NN), Support Vector Machines (SVM-s) and Tree Based Models. Major advantage of SVM-s over NN is of minimizing a bound on the generalization error of model rather than minimizing a bound on mean square error over the data set as done in NN. Tree Based approach divides the problem into a small number of sub problems to reach at a conclusion. Number of data was created for different parameters of beam to calculate the reinforcement using limit state method for creation of models and validation. The results from this study suggest a remarkably good performance of tree based and SVM-s models. Further, this study found that these two techniques work well and even better than Neural Network methods. A comparison of predicted values with actual values suggests a very good correlation coefficient with all four techniques.

Keywords: Linear Regression, M5 Model Tree, Neural Network, Support Vector Machines.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1082405

References:

[1] M. A. Austin and J. L. Preston, "Solid modeling of R.C.Beams: I. Data Structures and Algorithms" Journal of Computing in Civil Engineering, ASCE, Vol. 6 (4), pp. 389-403, 1992.
[2] H. M. Chen, K. H. Tsai, G. Z. Qi, J.C.S. Yang, and F. Aminy, "Neural Network for Structure Control", Journal of Computing in Civil Engineering, ASCE, Vol. 9 (2), pp. 168-176, 1995.
[3] D. P. Solomatine and K. N. Dulal, "Model trees as an alternative to neural networks in rainfall-runoff modeling", Journal of Hydrological Sciences, Vol. 48 (3), pp. 399-411, 2003.
[4] I. H. Witten and E. Frank, Data Mining: Practical Machine Learning Tools and Techniques with Java Implementation. Morgan Kaufmann Publisher, 2000.
[5] M. S. Nagesha, P. P. Ramugade, R. Potdar, and S. V. Patil , "Rapid estimation of Concrete Strength using predictive tools", The Indian Concrete Journal, pp. 947-951, 2003.
[6] J. L. Preston and M. A. Austin, "Solid Modeling of R.C.Beams: II. Computational environment", Journal of Computing in Civil Engineering, ASCE, Vol. 6 (4), pp. 404-416, 1992.
[7] J. L. Rogers, "Simulating structural analysis with Neural Network",, Journal of Computing in Civil Engineering, ASCE, Vol. 8(2), pp. 252-265, 1994.
[8] J. R. Quinlan., "Learning with Continuous Classes", Proceedings AI-92 (Adams & Sterling), Singapore, World Scientific, pp. 343-348, 1992.
[9] Y. B. Dibike, S. Celickov, and D. Solomatine, "Support Vector Machines: Review and Applications in Civil Engineering.2000", 2nd Joint Work Shop on Application of AI in Civil Engineering, March 2000, Cotbus, Germany, 2000.