Experimental and numerical studies on progressive debonding of grouted rock bolts

Understanding the mechanism of progressive debonding of bolts is of great significance for underground safety.In this paper,both laboratory experiment and numerical simulation of the pull-out tests were performed.The experimental pull-out test specimens were prepared using cement mortar material,and a relationship between the pull-out strength of the bolt and the uniaxial compressive strength(UCS)of cement mortar material specimen was established.The locations of crack developed in the pull-out process were identified using the acoustic emission(AE)technique.The pull-out test was reproduced using 2D Particle Flow Code(PFC^(2D))with calibrated parameters.The experimental results show that the axial displacement of the cement mortar material at the peak load during the test was approximately 5 mm for cement-based grout of all strength.In contrast,the peak load of the bolt increased with the UCS of the confining medium.Under peak load,cracks propagated to less than one half of the anchorage length,indicating a lag between crack propagation and axial bolt load transmission.The simulation results show that the dilatation between the bolt and the rock induced cracks and extended the force field along the anchorage direction;and,it was identified as the major contributing factor for the pull-out failure of rock bolt.

An investigation of machine learning techniques to estimate minimum horizontal stress magnitude from borehole breakout

Borehole breakout is a widely utilised phenomenon in horizontal stress orientation determination,and breakout geometrical parameters,such as width and depth,have been used to estimate both horizontal stress magnitudes.However,the accuracy of minimum horizontal stress estimation from borehole breakout remains relatively low in comparison to maximum horizontal stress estimation.This paper aims to compare and improve the minimum horizontal stress estimation via a number of machine learning(ML)regression techniques,including parametric and non-parametric models,which have rarely been explored.ML models were trained based on 79 laboratory data from published literature and validated against 23 field data.A systematic bias was observed in the prediction for the validation dataset whenever the horizontal stress value exceeded the maximum value in the training data.Nevertheless,the pattern was captured,and the removal of systematic bias showed that the artificial neural network is capable of predicting the minimum horizontal stress with an average error rate of 10.16%and a root mean square error of 3.87 MPa when compared to actual values obtained through conventional in-situ measurement techniques.This is a meaningful improvement considering the importance of in-situ stress knowledge for underground operations and the availability of borehole breakout data.