Rock tensile strength (TS) is an essential parameter for designing structures in rock-based projects such as tunnels, dams, and foundations. During the preliminary phase of geotechnical projects, rock TS can be determined through laboratory works, i.e., Brazilian tensile strength (BTS) test. However, this approach is often restricted by laborious and costly procedures. Hence, this study attempts to estimate the BTS values of rock by employing three non-destructive rock index tests. BTS predictive models were developed using 127 granitic rock samples. Since the simple regression analysis did not yield a meaningful result, the development of models that integrate multiple input parameters were considered to improve the prediction accuracy. The effects of non-destructive rock index tests were examined through the use of multiple linear regression (MLR) and adaptive neuro-fuzzy inference system (ANFIS) approaches. Different strategies and scenarios were implemented during modelling of MLR and ANFIS approaches, where the focus was to consider the most important parameters of these techniques. As a result, and according to background and behaviour of the ANFIS (or neuro-fuzzy) model, the predicted values obtained by this intelligent methodology are closer to the actual BTS compared to MLR which works based on linear statistical rules. For instance, in terms of system error and a-20 index, values of (0.84 and 1.20) and (0.96 and 0.80) were obtained for evaluation parts of ANFIS and MLR techniques, which revealed that the ANFIS model outperforms the MLR in forecasting BTS values. In addition, the same results were obtained through ranking systems by the authors. The neuro-fuzzy developed in this study is a strong technique in terms of prediction capacity and it can be used in the other rock-based projects for solving relevant problems.

This study applied two feed-forward type computational methods to estimate the Unconfined Compression Strength (UCS) of stabilized peat soil with natural filler and cement. For this purpose, experimental data was obtained via testing of 271 samples at different natural filler and cement mixture dosages. The input parameters for the developed UCS (output) model were: 1) binder dosage, 2) coefficient of compressibility, 3) filler dosage, and 4) curing time. The model estimated the UCS through two types of feed-forward Artificial Neural Network (ANN) models that were trained with Particle Swarm Optimization (ANN-PSO) and Back Propagation (ANN-BP) learning algorithms. As a means to validate the precision of the model two performance indices i.e., coefficient of correlation (R²) and Mean Square Error (MSE) were examined. Sensitivity analyses was also performed to investigate the influence of each input parameters and their contribution on estimating the output. Overall, the results showed that MSE_(PSO) < MSE_(BP) while R²_(PSO) > R²_(BP); suggesting that the ANN-PSO model better estimates the UCS compared to ANN-BP. In addition, on the account of sensitivity analysis, it is found that the binder and filler content were the two most influential factors whilst curing period was the least effective factor in predicting UCS.

The study examined the use of recycled tire-derived aggregate (TDA) mixed with kaolin for retaining wall applications. The effects of the TDA content on the geotechnical properties of TDA-kaolin specimens such as the internal friction angle, maximum dry density (MDD), optimum moisture content (OMC) and saturated density (SD) were investigated. A total of 13 physical model tests were performed on a polymer concrete retaining wall using kaolin and TDA-kaolin mixtures as backfill material. Powdery, shredded, small-sized granular (1–4 mm) and large-sized granular (5–8 mm) TDA were mixed with kaolin at contents of 0%, 20%, 40%, and 60% by weight. The lateral wall displacement was measured on a fabricated steel strip footing close to the wall during loading. Lateral wall displacement also was simulated using finite element (FE) software (Optum G2). The results indicated that the addition of 60% TDA decreased the internal friction angle of the samples up to 8% compared to pure kaolin. In addition, the TDA particles caused the MDD of the TDA-kaolin samples to decrease up to 45%. The physical modeling results indicated that the kaolin samples mixed with 60% shredded TDA showed the highest elasticity in all tests at the failure moment of the footing.