Use of artificial neural networks to estimate installation damage of nonwoven geotextiles

This paper presents a feed forward back-propagation neural network model to predict the retained tensile strength and design chart in order to estimation of the strength reduction factors of nonwoven geotextiles due to installation process. A database of 34 full-scale field tests were utilized to train, validate and test the developed neural network and regression model. The results show that the predicted of retained tensile strength using the trained neural network are in good agreement with the tests results. The predictions obtained from the neural network are much better than regression model as the maximum percentage of error for training data is less than 0.87% and 18.92%, for neural network and regression model, respectively. Based on the developed neural network, a design chart has been established. As a whole, installation damage reduction factors of the geotextile increase in the aftermath of compaction process under lower as-received grab tensile strength, higher imposed stress over the geotextiles, larger particle size of the backfill, higher relative density and weaker subgrades.