The application of neural network in lifetime prediction of concrete

Abstract

There are many difficulties in concrete endurance prediction, especially in accurate predicting service life of concrete engineering. It is determined by the concentration of SO₄ ²⁻/Mg²⁺/Cl⁻/Ca²⁺, reaction areas, the cycles of freezing and dissolving, alternatives of dry and wet state, the kind of cement, etc., In general, because of complexity itself and cognitive limitation, endurance prediction under sulphate erosion is still illegible and uncertain, so this paper adopts neural network technology to research this problem. Through analyzing, the paper sets up a 3—levels neural network and a 4—levels neural network to predict the endurance under sulphate erosion. The 3—levels neural network includes 13 inputting nodes, 7 outputting nodes and 34 hidden nodes. The 4—levels neural network also has 13 inputting nodes and 7 outputting nodes with two hidden levels which has 7 nodes and 8 nodes separately. In the end the paper give a example with laboratorial data and discussion the result and deviation. The paper shows that deviation results from some faults of training specimens: such as few training specimens and few distinctions among training specimens. So the more specimens should be collected to reduce data redundancy and improve the reliability of network analysis conclusion.

Keywords

neural network / concrete structure / lifetime prediction

References

[1] Shang gang, Liu Lisheng, Zhong Luo. The Application of Neural Network in Girder Structure.Journal of Wuhan University of Technology in chinese, 1998, 20 (2)

[2] Shang Gang, Zhong Luo, Liulisheng. The Weight Analysis of Structure Designing.Computer Development in Chinese, 1998, 8 (1)

[3] Yanchun Li. The Study of Artificial Neural Network Applying to Parameter Discrimination of Surrounding Rocks in Underground Caves. Pattern Recognization And Artificial Intelligence, 1997, 1(1): 9-9.

[4] Zhao Kehua. Neural Network Model of Temperature Prediction in the Pacific.Computer Application, 1999, 17 (4)

[5] Liqingfu, Zhaoguofan, Wanghengdong. Prediction and Evaluation of Concrete Endurance.Concrete (in Chinese), 1995, (3)

[6] Yao Qijun. Endurance Prediction of Reinforced Concrete Structure.Concrete and Cement Products (in chinese), 1995, (2)

[7] Ma Baoguo, Peng Guanliang, Hu Shuguang Study and Application on the Expert System of Concrete Resist Reinforcing Steel Corrosion,Journal of Wuhan University of Technology (in chinese), 2000, 22 (3)

[8] Xia Hongxia, Song Huazhu, Zhong Luo. Expert System of the Resistivity of Corrosion of Steel Reinforcement in Concrete. Journal of Wuhan University of Technology in chinese, 1999, 21 (4)

[9] Ma Baoguo, Lu Llingnv, Hu Shuguang. Study and Application on the Pumpcrete Technology Expert System.Joural of Wuhan University of Technology—Mater. Sci. Ed. 1999, (2)

[10] Xia Hongxia, Liu Hanli, Zhong Luo, Hushuguang. The Method of Hirerarchical and Structured Mixed Knowledge Representation.Journal of Wuhan University of Technology in chinese, 1999, 21 (6)