Experimental Study and Soft Computing Modeling of the Unconfined Compressive Strength of Limestone Rocks Considering Dry and Saturation Conditions

Unconfined compressive strength (UCS) of intact limestone rocks is very significant in geotechnical engineering in order to design structures that are currently being built on/in these rocks safely and economically. Obtaining core samples and testing them in laboratory according to the available standards is very expensive and time consuming. Therefore, developing novel models to predict the UCS of limestone rocks using physical properties and non-destructive tests is crucially needed. Hence, the research in this paper has been conducted to address this aim. 104 samples of intact limestone rocks have been collected from two provinces in north of Iraq (Sulaymaniyah and Mosul). The UCS, Schmidt hammer rebound number, ultrasonic pulse velocity, dry density, saturated density, and porosity have been obtained for these samples. One-dimensional regression analysis and advanced evolutionary polynomial regression (EPR-MOGA) analysis have been conducted using the obtained results. It was found that the EPR-MOGA analysis showed improved prediction performance and generally the prediction accuracy increases as the number of the variables increases. The models developed using EPR-MOGA have been compared to a simple regression equation proposed in the literature for north of Iraq limestone rocks, where it was found that the new models outperform the available correlation. The proposed models could be of significant help to practitioners when the compression testing machine is not available or when it is difficult to obtain intact samples with the appropriate length to diameter ratio. The proposed models could also serve as a tool to do independent quality control check of UCS laboratory results.