Find in Library

Pile settlement (SP) socketed to rock has taken vital regard. Despite introducing some design methods to measure SP, applying the novel and efficient prediction model with satisfactory performance is pivotal. The main goal of this study is to find out the applicability of applying two hybrid multi-layer perceptron neural network (MLP) models in predicting the SP in the Klang Valley Mass Rapid Transit (KVMRT) project constructed operated in Kuala Lumpur, Malaysia. Various hidden layers of models were examined to have comprehensive, accurate and reliable outputs. Ant lion optimizer (ALO) and grasshopper optimization algorithm (GOA) was applied to identify each hidden layer’s optimal number of neurons. In this case, five parameters were considered as input variables and SP as output. Regarding ALO-MLP models, ALO-MLP1 has the lowest score (48), with R2 stood at 0.9382 and 0.93, and PI at 0.0416 and 0.0494 for the training and testing phases, respectively. In the training phase, best values of R2, RMSE and PI were belonged to MLP1, while MLP2 has the smallest value of MAE. However, in the testing phase, MLP model with two hidden layer has best values for all indices, which makes it the proposed MLP model with two hidden layers. The results show that ALO is more capable than GOA for determining the optimal neuron numbers of MLP. By summation of the ranking scores obtained from performance evaluation indices, although GOA-MLP models have acceptable performance, two layers of MLP optimized with ALO could be recognized as the proposed model.