Application of Neural Network in Identifying Soil Strata by CPT or CPTU Data

Abstract

In geotechnical engineering, assessment of the depth location of stratigraphic interfaces and the depth and thickness of thin layers can be critical in the design process. For example, stratigraphic interfaces can promote anisotropic soil strength response and potentially provide preferential slip planes that create slope instability. Similarly, the presence of thin, high permeability layers can alter groundwater flow regimes and rates of consolidation, which can hinder or accelerate methods of ground improvement. The piezocone penetration test (PCPT or CPTU) is an extension of the cone penetration test (CPT) and is able to measure cone tip resistance, sleeve friction and generated pore-water pressures simultaneously. The piezocone’s functionality is through the measured excess pore pressure profile, which reflects changes in the drainage conditions, and therefore soil conditions. In this paper the relationship between CPTU parameters and soil types and strata is analyzed, and the structure of a general regression neural network (GRNN) is designed, and the application program is programmed with MATLAB language. The results, identifying soil strata by CPTU, have confirmed that GRNN can be used to carry out the automatically identifying soil strata.