Optimized functional linked neural network for predicting diaphragm wall deflection induced by braced excavations in clays

Previous studies have shown that installation of cross walls in deep excavations can reduce lateral wall deflection to a very small amount. To predict the lateral wall deflection for excavations with cross walls, it is necessary to perform a three-dimensional numerical analysis because the deflection behavior of the diaphragm wall with cross walls is by nature three dimensional. However for the analysis and design of excavations, two-dimensional plane strain analysis is mostly used in practice . For this reason, based on the deflection behavior of continuous beams and the superimposition principle, an equivalent beam model suitable for two-dimensional plane strain analysis was derived to predict lateral wall deflection for excavations with cross walls. Three excavation cases were employed to verify the proposed model. Case studies confirm the proposed equivalent beam model for excavations with cross walls installed from near the ground surface down to at least more than half the embedded depth of the diaphragm wall. For the case with a limited cross-wall depth, the proposed model yields a conservative predicted lateral wall deflection.

Download Full-text

Evolutionary Fuzzy Support Vector Machine Forecast Model (EFSVM) for Predicting Diaphragm Wall Deflection in Deep Excavations

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.88-89.531 ◽

2011 ◽

Vol 88-89 ◽

pp. 531-531

Keyword(s):

Support Vector Machine ◽

Forecast Model ◽

Diaphragm Wall ◽

Support Vector ◽

Fuzzy Support Vector Machine ◽

Deep Excavations ◽

Wall Deflection

Removed due to author dispute.

Download Full-text

Neural network application in forecasting maximum wall deflection in homogenous clay

International Journal of Geo-Engineering ◽

10.1186/s40703-021-00158-z ◽

2021 ◽

Vol 12 (1) ◽

Author(s):

Khalid R. Aljanabi ◽

Osamah M. AL-Azzawi

Keyword(s):

Neural Network ◽

Earth Pressure ◽

Width Ratio ◽

Maximum Deflection ◽

Ann Model ◽

Relative Significance ◽

Wall Deflection ◽

Ann Models ◽

Network Application ◽

Input Variables

AbstractAn attempt was carried out by using a neural network to predict the maximum deflection and its position caused by braced excavation in homogeneous clay. Six input variables, including excavation depth, Ratio of EI wall/EI of brace, the vertical distance between bracing, Length to width ratio of an excavation, shear strength, and the coefficient of lateral earth pressure, were adopted. Two models were developed, one is to estimate the maximum deflection and the other one to estimate the position of maximum deflection. The ANN models were developed and verified using a database of (169) cases of actual measured and presumptive cases using the analysis with the Finite element of maximum deflection. A sensitivity analysis was accomplished, to examine the relative significance of the parameters that influence the maximum deflection of the wall and its position; it indicates that the Ratio of EI wall/EI of brace has the most significant effect on the maximum wall deflection, while the properties of the soil have the most considerable effects on the position. The results show that the ANN can reasonably forecast the magnitude of the maximum deflection of the wall, as well as its position. Design charts are developed based on the ANN model.

Download Full-text