Predicting Triaxial Compressive Strength and Young’s Modulus of Frozen Sand Using Artificial Intelligence Methods

TLDR

Frozen soils’ triaxial compressive strength and Young’s modulus are essential for tunneling and excavation, yet indirect estimation methods are scarce because laboratory testing is difficult, and no prior study has used AI to predict these properties. The study compares artificial neural network, adaptive neuro‑fuzzy inference system, and support vector machine models for predicting σtc and E of frozen sandy soils. Eighty‑two poorly graded sandy samples from a Tabriz subway borehole were used to train and evaluate the models. Temperature, confining pressure, strain rate, and yielding strain improve prediction accuracy, and the SVM model successfully predicts σtc and E.

Abstract

Mechanical properties of frozen soils (e.g., triaxial compressive strength, σtc and Young’s modulus, E) are important in tunnel, shaft, or open pit excavation projects. Although numerous attempts have been made to develop indirect methods to estimate unfrozen soils’ σtc and E values, this has not been done with frozen soils given the difficulty of preparing and conducting relevant laboratory tests. In this study, the accuracy of artificial neural network (ANN), adaptive neuro fuzzy inference system (ANFIS), and support vector machine (SVM) models, developed to predict σtc and E for frozen sandy soils, was compared. To the best of the authors’ knowledge, no study has predicted frozen soils’ σtc and E using these methods. Eighty-two poorly graded sandy soil samples from an urban subway borehole in Tabriz, Iran, were used to develop these models. It was found that temperature, confining pressure, strain rate, and yielding strain improved the accuracy of σtc and E prediction. Results indicate that SVM can successfully be used in predicting the σtc and E of frozen soils.