As one of the key techniques in the fully mechanized mining process, equipment selection and matching has a great effect on security, production and efficiency. The selection and matching of fully mechanized mining equipment in thin coal seam are restricted by many factors. In fully mechanized mining (FMM) faced in thin coal seams (TCS), to counter the problems existing in equipment selection, such as many the parameters concerned and low automation, an expert system (ES) of equipment selection for fully mechanized mining longwall face was established. A database for the equipment selection and matching expert system in thin coal seam, fully mechanized mining face has been established. Meanwhile, a decision-making software matching the ES was developed. Based on several real world examples, the reliability and technical risks of the results from the ES was discussed. Compared with the field applications, the shearer selection from the ES is reliable. However, some small deviations existed in the hydraulic support and scraper conveyor selection. Then, the ES was further improved. As a result, equipment selection in fully mechanized mining longwall face called 4301 in the Liangshuijing coal mine was carried out by the improved ES. Equipment selection results of the interface in the improved ES is consistent with the design proposal of the 4301 FMM working face. The reliability of the improved ES can meet the requirements of the engineering. It promotes the intelligent and efficient mining of coal resources in China.
Rockburst is a common engineering geological hazard. In order to evaluate rockburst liability in kimberlite at an underground diamond mine, a method combining generalized regression neural networks (GRNN) and fruit fly optimization algorithm (FOA) is employed. Based on two fundamental premises of rockburst occurrence, depth, σθ, σc, σt, B1, B2, SCF, Wet are determined as indicators of rockburst, which are also input vectors of GRNN model. 132 groups of data obtained from rockburst cases from all over the world are chosen as training samples to train the GRNN model; FOA is used to seek the optimal parameter σ that generates the most accurate GRNN model. The trained GRNN model is adopted to evaluate burst liability in kimberlite pipes. The same eight rockburst indicators are acquired from lab tests, mine site and FEM model as test sample features. Evaluation results made by GRNN can be confirmed by a rockburst case at this mine. GRNN do not require any prior knowledge about the nature of the relationship between the input and output variables and avoid analyzing the mechanism of rockburst, which has a bright prospect for engineering rockburst potential evaluation.