Abstract
This paper presents a new method of using ANN (Artificial Neural Networks) to solve the inverse problem: predicting reinforced concrete (RC) beams flexural load rating (ratio of flexural load to ultimate bearing capacity) given apparent damage parameter (crack width, crack height, deflection). A hybrid algorithm (G-Prop) that combines a genetic algorithm (GA) and BP (back-propagation) is used to train ANN with a single hidden layer. The GA selects the initial weights and changes the number of neurons in the hidden layer through the application of specific genetic operators. The case study shows that ANN based on GA and BP is a powerful instrument for predicting flexural load rating and further for evaluating RC beams safety.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
China ministry of communications standards.: Identification of Load carrying capacity for existing highway bridge (trial implementation ) (in chinese). People’s Communications Publishing House, Beijing (1989)
Dajun, D.: Crack resistance, crack and stiffness of reinforced concrete element (in chinese). Nanjing Technical college press, Nanjing (1986)
Park, R., Paulak, T.: Reinforced Concrete Structures. John Wiley & Sons, Canada (1975)
China standard (JTJ 073-96).: Technical Specifications of Maintenance for Highway (in chinese). People’s Communications Publishing House, Beijing (1996)
Guanhua, Z.: Flexural crack parameter, inspection and evaluation of existing RC bridges (in chinese). Dalian university of technology, Dalian (2003)
Simon, H.: Neural Networks: a comprehensive foundation. Tsinghua University Press, Beijing (2001)
Goldberg, D.E.: Genetic Algorithms in search, Operatimization, and Machine Learning. Addison-Wesley, Reading (1989)
Yong, L., Lishan, K., Yuping, C.: Genetic algorithms. In: Non-numerical parallel algorithms, vol. 2, Science Press, Beijing (2000)
Mohamed, A., Mahmoud, M.A., Kiefa, A.: Neural network solution of the inverse vibration problem. NDT&E. Int. 32, 91–99 (1999)
Suh, M.-W., Shim, M.-B.: Crack identification of using hybrid neuro-genetic technique. J. Sound and Vibration. 238(4), 617–635 (2000)
Castillo, P.A., Merelo, J., Prieto, A., Rivas, V., Romero, G.: G-Prop: Global optimization of multiplayer perceptrons. Neurocomputing 35, 149–163 (2000)
Shuntian, L., Yang, S.: Systematic analysis and design based on MATLAB: neural networks (in chinese). Sian electronic and technical university press, Sian (1999)
Yang, S.: MATLAB essence and dynamic emulation tool SIMULINK (in chinese). North-West industry press, Sian (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yang, Z., Huang, C., Qu, J. (2004). Inversing Reinforced Concrete Beams Flexural Load Rating Using ANN and GA Hybrid Algorithm. In: Yin, FL., Wang, J., Guo, C. (eds) Advances in Neural Networks - ISNN 2004. ISNN 2004. Lecture Notes in Computer Science, vol 3174. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28648-6_125
Download citation
DOI: https://doi.org/10.1007/978-3-540-28648-6_125
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22843-1
Online ISBN: 978-3-540-28648-6
eBook Packages: Springer Book Archive