Settlement Prediction Using Support Vector Machine (SVM)-Based Compressibility Models: A Case Study

摘要

The magnitude of soil settlement depends on several variables such as the compression index, C-c, and recompression index, C-r, which are determined by a consolidation test. This laboratory test is time consuming and labor intensive, thus efforts to correlate the compressibility indexes and soil index properties have been made. In this study, soil compressibility prediction models are enhanced by the support vector machine (SVM) algorithm, and the performances of those correlations are tested via field verification in terms of settlement calculation. The field verification portion of the study consists of identifying sites with borings, consolidation tests, and measured settlement from overlying load. Soil layers, within the influence zone of settlement, are tested to obtain soil index parameters. Once a complete soil profile has been established, a series of settlement analyses were performed. Settlement predictions were made based on both predicted and measured C-r for each soil layer. An additional settlement prediction was made using a rule of thumb equating C-c to C-r. The predicted settlements were then compared to the measured settlement taken in close proximity. Upon conclusion, using the C-r and C-c correlations provides comparable settlement predictions compared to measured settlement and the predicted C-r (using a correlation from predicted C-c) exhibits the strongest settlement predictions. The predicted settlements are lower than the measured settlements for both site locations. This leads one to believe that the influence zone of settlement may be deeper than originally considered.