The shear strength of rockfill materials (RFM) is an important engineering parameter in the design and audit of geotechnical structures. In this paper, the predictive reliability and feasibility of random forests and Cubist models were analyzed by estimating the shear strength from the relative density, particle size, distribution (gradation), material hardness, gradation and fineness modulus, and confining (normal) stress. For this purpose, case studies of 165 rockfill samples have been applied to generate training and testing datasets to construct and validate the models. Thirteen key material properties for rockfill characterization were selected to develop the proposed models. Validation and comparison of the models have been performed using the root mean square error (RMSE), coefficient of determination (R2), and mean estimation error (MAE) between the measured and estimated values. A sensitivity analysis was also conducted to ascertain the importance of various inputs in the prediction of the output. The results demonstrated that the Cubist model has the highest prediction performance with (RMSE = 0.0959, R2 = 0.9697 and MAE = 0.0671), followed by the random forests model with (RMSE = 0.1133, R2 = 0.9548 and MAE= 0.0665), the artificial neural network (ANN) model with (RMSE = 0.1320, R2 = 0.9386 and MAE = 0.0841), and the conventional multiple linear regression technique with (RMSE = 0.1361, R2 = 0.9345 and MAE = 0.0888). The results indicated that the Cubist and random forests models are able to generate better predictive results of the shear strength of RFM than ANN and conventional regression models. The Cubist model was considered to be more promising for interpreting the complex relationships between the influential properties of RFM and the shear strengths of RFM to some extent, which can be extremely helpful in estimating the shear strength of rockfill materials.

No abstract

No abstract

Thin spray-on liners (TSLs) are attracting attention as effective rock support reinforcement in underground mines. They have the potential to increase roadway development rates and provide resistance at small rock surface displacements. To study the reinforcement provided by a TSL when applied onto a pillar surface, the support mechanism of TSL-coated rock samples was investigated, thereby providing a basis for studying the effect of TSL confinement on rock pillars. A polymeric material liner was applied to three types of rock (siltstone, sandstone and granite), and details of the sample preparation and loading procedures are presented. The results of rock failure tests indicate that significant strength improvement and enhancement of post-failure characteristics developed for the TSL-encapsulated samples. TSL reinforcement of the weaker rocks appears to be better than that of the stronger rocks. It is concluded that effective rock reinforcement occurs in the case when the tensile strength of the TSL material is greater than the tensile strength of the rock; the TSL reinforcement of stronger rock types may not be as effective. The test results obtained are consistent and conclusive.

Thin spray-on liners (TSLs) have been attracting increasing attention as an alternative to steel mesh in underground roadway support. In order to investigate the shear strength of glass fibre reinforced TSLs, an improved punch test was developed: the steel ring is replaced by TSL plates and four screws are used to tighten the TSL sample between the clamping plates to ensure stable and symmetrical loading. Four different glass fibre contents were tested to evaluate the effect of glass fibre reinforcement on the shear strength of TSLs. The effect of loading rate was studied. The results suggest that the steel punch can shear through the polymer sheet well and the failure mode can be easily identified. The results are consistent and easily calculated. The shear strength increases with glass fibre content. The TSL material samples showed good linear behaviour prior to reaching ultimate load and ductile behaviour that reflects the fibre reinforcement of failed resin during the yielding stage of the sample, which is beneficial to support in underground mines. Although there may be some impact of the shearing rate on the shear strength, the effect is negligible for the loading rates used. Shear strength testing of glass fibre reinforced thin spray-on liner Q. QIAO*, J. NEMCIK* and I. PORTER* Thin spray-on liners (TSLs) have been attracting increasing attention as an alternative to steel mesh in underground roadway support. In order to investigate the shear strength of glass fibre reinforced TSLs, an improved punch test was developed: the steel ring is replaced by TSL plates and four screws are used to tighten the TSL sample between the clamping plates to ensure stable and symmetrical loading. Four different glass fibre contents were tested to evaluate the effect of glass fibre reinforcement on the shear strength of TSLs. The effect of loading rate was studied. The results suggest that the steel punch can shear through the polymer sheet well and the failure mode can be easily identified. The results are consistent and easily calculated. The shear strength increases with glass fibre content. The TSL material samples showed good linear behaviour prior to reaching ultimate load and ductile behaviour that reflects the fibre reinforcement of failed resin during the yielding stage of the sample, which is beneficial to support in underground mines. Although there may be some impact of the shearing rate on the shear strength, the effect is negligible for the loading rates used. INTRODUCTIONThin spray-on liners (TSLs) are a relatively new form of rock support in underground coal mines. As an active support technique, it is known that a TSL is able to take action even if only small rock movement occurs, which is desirable for rock support. As steel mesh is of a passive nature and does not contribute to roadway skin reinforcement, TSLs are currently being investigated as an effective technology. ToughSkin, a fibre glass reinforced polymeric material liner developed at the University of Wollongong, has properties that sati...