Prediction of Soil Properties from PCPT Pore Pressure Measurements Using Data Fusion

ABSTRACT: Although the piezocone penetration test (PCPT) has several advantages over traditional methods of sampling and laboratory analysis in determining representative properties of a soil deposit, the existing methods used to infer soil properties from PCPT data are not always reliable due to the complexity of cone penetration. In this study, it is proposed that the process of “data fusion” can be used to estimate soil properties, including overconsolidation ratio (OCR), coefficient of lateral earth pressure at rest (Ko), and undrained shear strength (su), from PCPT pore pressure measurements, and that data fusion algorithms, through training, may be able to overcome some of the limitations of the current PCPT interpretation methods. The general regression neural network (GRNN), a feature-level data fusion algorithm, was used to transform the features extracted from the raw piezocone sensor data into estimates of OCR, Ko, and su. The benefits of fusing data from multiple sensors were evaluated by building multiple models from data obtained using one and two piezocone sensors and comparing the accuracy of the model predictions. Data fusion model predictions were also compared with the estimates obtained using existing interpretation methods.