Application of an Artificial Neural Network (ANN) Model to Determine the Value of the Damping Ratio (D) of Clay Soils

Abstract

The properties and behavior of soils depend on many factors. The interaction of individual factors is difficult to determine by traditional statistical methods due to their interdependence. The paper presents a procedure of creating an artificial neural network (ANN) model to determine the value of the damping ratio (D) of clay soils. The main purpose of this paper is to compare the appropriateness of ANN model application with empirical formulas described in the literature. The ANN model was developed using a series of laboratory tests of the damping ratio performed in the Resonance Column. Predicted values of the damping ratio of clay soils obtained from the ANN model are characterized by high convergence (coefficient of determination R2 = 0.976). In comparison with other published empirical formulas, the ANN model showed an improvement in the prediction accuracy. What is more, ANN models proved to be more flexible compared to formulas and relationships with a predetermined structure, and they were well suited to modeling the complex behavior of most geotechnical engineering materials, which, by their very nature, exhibit extreme variability. In conclusion, ANNs have the potential to predict the damping ratio (D) of clay soils and can do much better than traditional statistical techniques.

Laboratory Testing and Analysis of Clay Soil Stabilization Using Waste Marble Powder

“…The use of artificial neural networks (ANNs) to predict mechanical properties of stabilized soils, such as ultrasonic pulse velocity (UPV) and unconfined compressive strength (UCS), has gained popularity in recent years. However, the majority of existing studies have focused on ANN modeling of soil stabilization with lime or cement [27][28][29][30][31]. Despite the proven effectiveness of waste marble powder (WMP) as a sustainable soil stabilizer [8][9][10][11], few studies have investigated the potential of ANNs to model clay soil stabilization using WMP.…”

Prediction of Normalized Shear Modulus and Damping Ratio for Granular Soils Over a Wide Strain Range Using Deep Neural Network Modelling

“…Lendo-Siwicka et al [27] introduced an ANN model for determining the damping ratio of clay soils, addressing the complexities arising from the interdependence of soil properties. Through laboratory tests using the resonance column method, the ANN model exhibited high convergence (R 2 = 0.976) in predicting the damping ratio, surpassing the accuracy of existing empirical formulas.…”