Artificial neural networks for predicting the maximum surface settlement caused by EPB shield tunneling

摘要: Abstract Numerous empirical and analytical relations exist between shield tunnel characteristics surface subsurface deformation. Also, 2-D 3-D numerical analyses have been applied to such tunneling problems. Similar but substantially fewer approaches developed for earth pressure balance (EPB) tunneling. In the Bangkok MRTA project, data on ground deformation operation were collected. The sizes are practically identical conditions over long distances comparable, which allow one establish relationships EPB – hand, deformations other hand. After using information identify ground- EPB-characteristic greatest influence movements, an approach based artificial neural networks (ANN) was used develop predictive relations. Since method has ability map input output patterns, ANN enable all influencing parameters settlements. Combining extensive computerized database knowledge of what influences settlements, can become a useful method. This paper attempts evaluate potential as well limitations predicting settlements caused by optimal network models this objective.