Estimating cement take and grout efficiency on foundation improvement for Li-Yu-Tan dam

The cement take needed for dam foundation improvement with grout-curtain is difficult to estimate due to the complexity of the rock foundation and the great number of Lugeon tests involved in the analysis. Therefore, this study adopted the mean method, the linear regression method, and the back-propagation neural network (BPN) method to analyze the grout-curtain construction data of the Li-Yu-Tan dam, Taiwan, in order to estimate the cement take needed. The samples analyzed included data from 3532 grout sections. The data from the first half of the grout-curtain construction were used to derive the parameters of the predictive schemes, and then the second half of the grout-curtain construction's data were used to test the accuracy of those schemes. The accuracy levels estimated by these three methods on gross cement take were 71.8%, 59.8%, and 75.3% for the mean method, the linear regression method and the BNP method, respectively. All accuracy levels estimated by these three methods were higher than the original design level of 43.4%. Furthermore, the efficiency of the grout improvement in the studied cases were confirmed by observing the changes of the distribution curve of the Lugeon value following each grout sequence. The method proposed is intelligible and can be applied in other situations.

[1]  Yasuhisa Hirota,et al.  PREDICTION OF GROUT TAKE IN DAM FOUNDATION GROUTING , 1990 .

[2]  M. Schaap,et al.  Neural network analysis for hierarchical prediction of soil hydraulic properties , 1998 .

[3]  Wallace Hayward Baker,et al.  Grouting in Geotechnical Engineering , 1982 .

[4]  H. Yeh,et al.  Solution for Flow Rates across the Wellbore in a Two-Zone Confined Aquifer , 2002 .

[5]  Yoshikazu Yamaguchi,et al.  PERMEABILITY AND LUGEON VALUES OF DAM FOUNDATIONS , 1989 .

[6]  Ken Weaver,et al.  Dam Foundation Grouting , 1991 .

[7]  Isao Shibata.  THE DETERMINATION OF A RATIONAL INJECTION PRESSURE RELATED TO IN-SITU STRESS IN DAM FOUNDATION GROUTING , 1991 .

[8]  Yi Huang,et al.  The introduction of neural network system and its applications in rock engineering , 1998 .

[9]  A. Goh.  Seismic liquefaction potential assessed by neural networks , 1994 .

[10]  Friedrich-Karl Ewert.  Rock Grouting: With Emphasis on Dam Sites , 1985 .

[11]  A. C. Houlsby.  Construction and design of cement grouting : a guide to grouting in rock foundations , 1990 .

[12]  Imad A. Basheer,et al.  Selection of Methodology for Neural Network Modeling of Constitutive Hystereses Behavior of Soils , 2000 .

[13]  Musharraf Zaman,et al.  Modelling of shearing behaviour of a residual soil with Recurrent Neural Network , 1998 .

[14]  A. T. C. Goh,et al.  Back-propagation neural networks for modeling complex systems , 1995, Artif. Intell. Eng..

[15]  Rui Zhao,et al.  Stress-Strain Modeling of Sands Using Artificial Neural Networks , 1995 .