To alleviate the environmental problems caused by scrap tire and tailings disposal, the performance of recycled tire polymer fiber (RTPF)-reinforced cemented paste backfill (CPB) was investigated. Ordinary CPB, commercial poly-propylene fiber (CPPF) and reinforced CPB were also investigated for comparison. Slump tests, unconfined compression tests and a cost–benefit analysis were conducted. The results indicate that the flowability of the RTPF-reinforced CPB decreased with the increasing fiber content. The failure strain, unconfined compressive strength, and toughness values were generally higher than that of ordinary CPB (i.e., CPB without any fiber reinforcement). However, the mechanical properties would not be improved continuously with increasing RTPF content. It was found that the inclusion of RTPFs achieved the best improvement effect with the best mechanical properties of CPB at the fiber content of 0.6%. The failure mode of the RTPF-reinforced CPB was safer than that of the ordinary CPB. Microscopic observations indicated that the bond between RTPFs and the CPB matrix could affect the mechanical properties of the RTPF-reinforced CPB. From the cost–benefit analysis, the inclusion of RTPFs to reinforce CPB could gain relatively high mechanical properties with a low material cost.

This study aimed to investigate the feasibility of using a model based on particle swarm optimization (PSO) and support vector machine (SVM) to predict the unconfined compressive strength (UCS) of cemented paste backfill (CTB). The dataset was built based on the experimental UCS values. Results revealed that the categorized randomly segmentation was a suitable approach to establish the training set. The PSO performed well in the SVM hyperparameters tuning; the optimal hyperparameters for the SVM to predict the UCS of CTB in this study were C = 71.923, ε = 0.0625, and γ = 0.195. The established model showed a high accuracy and efficiency on the prediction work. The R² value was 0.97 and the MSE value was 0.0044. It was concluded that the model was feasible to predict the UCS of CTB with high accuracy and efficiency. In the future, the accuracy and robustness of the prediction model will be further improved as the size of the dataset continues to grow.

Increasing amounts of tailings and waste rubber tires have caused threats to the environment. In order to reuse these solid wastes, this study proposed a cemented tailings material containing crumb rubber recovered from waste tires. Unconfined compression tests and thermal conductivity measurements were conducted to evaluate the feasibility and performance of the proposed cemented tailings. Results revealed that the stress-strain behavior of the cemented tailings changed by the inclusion of crumb rubber. The unconfined compressive strength of cemented tailings decreased with increasing crumb rubber content. The inclusion of crumb rubber increased the failure strain and nonlinearity index of the cemented tailings. It was found that the addition of 4% crumb rubber provided the greatest improvement in ductility. The increase of the rubber content further increased the thermal insulation capacity of the cemented tailings. The low stiffness and the dimpled surface of the crumb rubber were responsible for the reduced compressive strength and thermal conductivity of the cemented tailings. In conclusion, the crumb rubber had both positive and negative effects on the cemented tailings. In practical application, the rubber admixture amount should be flexibly adjusted for different use case to make the cemented tailings material show the most suitable performance characteristic.

Machine learning based on the support vector machine algorithm was used for the prediction of the unconfined compressive strength of rubber fiber modified cemented paste backfill. Grid analysis was used to find the optimal hyper-parameters. The SVM model was well trained on the training set, and performed well on the testing set. Analysis results showed that the SVM model achieved a higher accuracy. The squared correlation coefficient values were 0.9914 and 0.9321 on the training set and testing set, respectively. It is recommended that laboratories around the world could share UCS tests results of CPB to expand the dataset for the training of prediction models.

Mine tailings disposal has been a serious environmental issue for decades. The wide application of cemented tailings backfill (CTB) technology could indirectly abate tailings pollution by recycling the tailings for backfilling. CTB constitutive modeling helps with design by improving the understanding of its compressive behavior. This study focused on CTB intelligent constitutive modeling considering the coupled effects of the cement content and saturation state. An artificial intelligence model was established and utilized based on particle swarm optimization (PSO) and the support vector machine (SVM). CTB samples with different cement contents and water saturation states were prepared, and unconfined compression tests were conducted to obtain the dataset. We verified the feasibility of using integrated PSO and SVM (P-S) in the CTB constitutive model using experimental data. We analyzed model errors. The results showed that the CTB stress strain curve was complex and nonlinear and could be significantly affected by the saturation states. PSO was feasible and efficient for tuning the SVM hyperparameters. The lowest minimum MSE value of 0.0108 was achieved in the eighth iteration. The PSO and SVM modeling was indicated to be accurate in the CTB constitutive model (a high R-square value of 0.9935 and a low mean squared error value of 0.001664 were achieved on the testing set). This model may accelerate the CTB structure design process.

Backfilling mining method is a green mining method which is being used widely, nevertheless, the uniaxial compressive strength (UCS) of the cement backfill paste (CPB) on site is difficult to measure, and it is impossible to know the internal cementation, for this reason, the rebound method is improved and introduced in this paper. Standard specimens of CPB were made and cured for different curing age under standard curing conditions. The hardness test of each part of the CPB is completed, the unconfined compression test is carried out, and the functional model of the hardness of each part of the CPB is established, which was a function of radius and age. Based on the nonuniformity of the filling material, the failure mode of CPB is analyzed and verified in the test. The results show that the exponential function model is more suitable for the relationship between the external hardness and the overall strength, and this conclusion is of great significance in construction site. In addition, the corresponding relationship between hardness and local strength was calculated and verified, the results show that the simple model can predict the variation of local strength with hardness better, and the quadratic function model is the best choice.