Search

Taking Nanliang Coal Mine thick seam spacing mining as the engineering background, aiming at the safety problem of dynamic rock pressure occurring when the lower coal seam is mined over the pillar of the overburden goaf, this paper studies the mechanism of rock pressure appearing when the working face crosses the pillar of the overburden goaf by means of physical similarity simulation experiment, theoretical analysis and field measurement. Based on the structure and movement characteristics of overlying strata crossing the coal pillar, the mechanical structure models of load calculation of coal pillar and failure and instability of key rock blocks are established respectively, and the resistance of support increases sharply when the coal pillar is located in the working face. Combining with the concrete conditions of the working face passing through the coal pillar, the measures for adjusting the inclination of the working face are proposed, and the field engineering application is carried out. The field monitoring results show that the prevention measures have obvious effect on preventing dynamic rock pressure during passing through coal pillars.

A new method using gradient boosting regression tree(GBRT) which is optimized by logistic regression(LR) to predict working resistance of hydraulic support is proposed, avoiding shortcomings of current determining methods. Add learning rate to GBRT to limit the learning rate of sub-models and prevent over-fitting; using LR to optimize sample parameters to establish LR-GBRT regression prediction model; the model is applied to predict resistance of hydraulic support, and the prediction result is compared with linear regression(LR), support vector model(SVM), decision tree regression(DTR), elastic net regression(EN). The results show that the model has better generalization performance and higher prediction accuracy. It can effectively predict resistance of hydraulic support .

The Zigui basin is one of the most landslide-prone areas where thousands of landslides are distributed. Performing the landslide susceptibility mapping is a heated issue in the area. Whereas, whether the random selection of the landslides or non-landslides grid cells are reasonable in research of landslide susceptibility mapping is the existence problem nowadays. Based on the two step cluster (TSC) algorithm and the self-organizing mapping - random forest (SOM-RF) model, a novel hybrid model is proposed to overcome the above drawbacks in this study. Rough set (RS) theory is employed as an attribute reduction tool to identify the significant influencing factors of landslides, and SOM is used to produce a preliminary landslide susceptibility mapping. Two step cluster algorithm is applied in telling apart the most reasonable True-Positive (TP) from landslide grid cells in high-susceptibility zones and the False-Positive (FP) in low-susceptibility zones. Afterwards, the TP and FP are imported into the RF model as samples to produce the improved landslide susceptibility mapping. The proposed method is utilized to develop landslide susceptibility mapping in the Zigui basin. Compared with the susceptibility mapping produced by RF model, which selects landslides and non-landslides grid cells randomly, the results of TSC and SOM-RF model demonstrates to have the superior prediction skill and higher reliability in landslides susceptibility mapping. [ABSTRACT FROM AUTHOR]