Though machine learning (ML) approaches have proliferated in the mechanical properties prediction of cemented paste backfill (CPB), their applications have not reached the peak potential due to the lack of more robust techniques. In the present contribution, the state-of-the-art ensemble learning method was employed for improved estimation of the unconfined compressive strength (UCS) of CPB. 126 UCS tests were conducted on two new tailings to provide an enlarged dataset. Tree-based ML approaches, namely, regression tree (RT), random forest (RF), and gradient boosting regression tree (GBRT), were chosen to be individual ML approaches. The ensemble learning framework was used to combine the optimum individual regressors by means of GBRT. 5-fold cross-validation was used as the validation method and the performance was evaluated using correlation coefficient (R). Hyper-parameters tuning was conducted using particle swarm optimization (PSO). The results show that the best training set size was 70%. PSO was robust in the hyper-parameters tuning since the R value between experimental and predicted UCS on the training set was progressively increased. The ensemble learning can be used to improve the UCS prediction of CPB. The R values between experimental and predicted UCS obtained by RT, RF, GBRT, the ensemble GBRT regressors were 0.9442, 0.9507, 0.9832, and 0.9837, respectively. The method presented in this study extends recent efforts for UCS prediction of CPB and can significantly accelerate the CPB design. INDEX TERMS Cemented paste backfill, unconfined compressive strength, estimating, ensemble learning, particle swarm optimization.
Based on the split Hopkinson pressure bar (SHPB) test system, dynamic impact tests of coal specimens under different impact pressures were carried out to study the relationship between the impact load and the size of crushed lump coal. Based on the theory of stress wave attenuation, the relationship between the blasting impact load in a single-hole blasting area of a coal seam and the load applied in an impact failure test of a coal specimen in the laboratory was established. According to the characteristics of the fragmentation distribution of the coal specimens destroyed under a laboratory impact load and the requirement of the minimum cost control of coal blasting in an open-pit coal mine, the fragmentation size range was divided into three groups: large-diameter, medium-diameter, and powder particles. Based on this range, the variation rule of the mass percentage of coal fragments with impact pressure was obtained. Established on the evaluation principle of the blasting effect in an open-pit coal mine, a good impact fragmentation effect was obtained. The good pressure range is 0.30 MPa≤P<0.90 MPa.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.