In northern Shaanxi province, the coal seam deposit conditions are generally characterized by large thickness and shallow depth of burial, the phenomenon of coal pillar sloughing is serious in the process of working face retrieval, which brings great potential danger to mine safety production. In this paper, by monitoring the stress and damage of the coal pillar in the field section, the stress changes and damage degree of the working face in different mine stages are determined. A new mechanical model of coal pillar in a thick coal seam is constructed and the stress changes and structural breakage law of each section are obtained, the stress transfers mechanism of overburden structure and the stress damage to coal pillar during the mining process of upper and lower section comprehensive mining working face is analyzed. The stress, microscopic damage, and the degree of sloughing in the coal pillar were significantly reduced by monitoring through the top plate hydraulic cracking pressure relief control program. The results of the study show that the extent of sloughing coal pillar and internal damage is closely related to the length of key block B of the masonry beam formed by the overlying rock layer and the position of the break line, by changing the orientation of the overlying masonry beam rock layer and the position and length of the tendency to break line, the sloughing coal pillar is effectively controlled and its stress and damage are reduced. We have achieved good results in control of the sloughing in the Hanjiawan coal mine and similar mines in northern Shaanxi.
Cemented paste backfill (CPB) is widely used in underground mining, and attracts more attention these years as it can reduce mining waste and avoid environmental pollution. Normally, to evaluate the functionality of CPB, the compressive strength (UCS) is necessary work, which is also time and money consuming. To address this issue, seven machine learning models were applied and evaluated in this study, in order to predict the UCS of CPB. In the laboratory, a series of tests were performed, and the dataset was constructed considering five key influencing variables, such as the tailings to cement ratio, curing time, solids to cement ratio, fine sand percentage and cement types. The results show that different variables have various effects on the strength of CPB. The optimum models for predicting the UCS of CPB are a support vector machine (SVM), decision tree (DT), random forest (RF) and back-propagation neural network (BPNN), which means that these models can be directly applied for UCS prediction in future work. Furthermore, the intelligent model reveals that the tailings to cement ratio has the most important influence on the strength of CPB. This research can boost CPB application in the field, and guide the artificial intelligence application in future mining.
Accurately evaluating rockburst intensity has attracted much attention in these recent years, as it can guide the design of engineering in deep underground conditions and avoid injury to people. In this study, a new ensemble classifier combining a random forest classifier (RF) and beetle antennae search algorithm (BAS) has been designed and applied to improve the accuracy of rockburst classification. A large dataset was collected from across the world to achieve a comprehensive representation, in which five key influencing factors were selected as the input variables, and the rockburst intensity was selected as the output. The proposed model BAS-RF was then validated by the dataset. The results show that BAS could tune the hyperparameters of RF efficiently, and the optimum model exhibited a high performance on an independent test set of rockburst data and new engineering projects. According to the ensemble RF-BAS model, the feature importance was calculated. Furthermore, the accuracy of the proposed model on rockburst prediction was higher than the conventional machine learning models and empirical models, which means that the proposed model is efficient and accurate.
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.