Prediction of standard penetration test N-value from dynamic probing light N-value using ANFIS and multiple regression models

ABSTRACT

Standard penetration test (SPT) is one of the most widely used tools to predict the soil properties. In recent years, the dynamic probing light (DPL) test has been performed more frequently for geotechnical applications because it is more cost-effective and fast. Since the majority of empirical equations of soil properties are related to SPT N-value, it is beneficial to find the best correlation between SPT and DPL N-values. In this study, the adaptive neuro-fuzzy inference system (ANFIS) and multiple regression (MR) are used to predict the correlation between SPT and DPL N-values. To achieve this goal, the soil properties of 64 sample specimens of silty clay were calculated at various depths. Three parameters including depth, total density, and DPL N-value were chosen as the input of the models.  Results show that both methods estimate the correlation between SPT and DPL N-values precisely. However, ANFIS predicts more accurately than multiple regression.

KEYWORDS:

• Adaptive neuro-fuzzy inference system (ANFIS)
• multiple regression (MR)
• dynamic probing light (DPL)
• standard penetration test (SPT)
• correlation
• silty clay
• in situ tests
• soft computing

Disclosure statement

No potential conflict of interest was reported by the authors.