Nong Zhang

Bio: Nong Zhang is an academic researcher from China University of Mining and Technology. The author has contributed to research in topics: Coal mining & Coal. The author has an hindex of 18, co-authored 123 publications receiving 1328 citations. Previous affiliations of Nong Zhang include Colorado School of Mines & North Dakota State University.

Development of ensemble learning models to evaluate the strength of coal-grout materials

Abstract: In the loose and fractured coal seam with particularly low uniaxial compressive strength (UCS), driving a roadway is extremely difficult as roof falling and wall spalling occur frequently. To address this issue, the jet grouting (JG) technique (high-pressure grout mixed with coal particles) was first introduced in this study to improve the self-supporting ability of coal mass. To evaluate the strength of the jet-grouted coal-grout composite (JG composite), the UCS evolution patterns were analyzed by preparing 405 specimens combining the influential variables of grout types, curing time, and coal to grout (C/G) ratio. Furthermore, the relationships between UCS and these influencing variables were modeled using ensemble learning methods i.e. gradient boosted regression tree (GBRT) and random forest (RF) with their hyperparameters tuned by the particle swarm optimization (PSO). The results showed that the chemical grout composite has higher short-term strength, while the cement grout composite can achieve more stable strength in the long term. The PSO-GBRT and PSO-RF models can both achieve high prediction accuracy. Also, the variable importance analysis demonstrated that the grout type and curing time should be considered carefully. This study provides a robust intelligent model for predicting UCS of JG composites, which boosts JG design in the field.

Borehole stress monitoring analysis on advanced abutment pressure induced by Longwall Mining

Abstract: The paper presented the research on the dynamic advanced abutment stress induced by longwall mining with borehole stress meters on mining side coal mass. Twenty vibrating wire borehole stress meters were installed into the extracting coal mass wall of a first mining roadway of 910 m depth in Zhuji Coal Mine, China, and were used to monitor dynamic changes in vertical and horizontal stresses. Three months of continuous monitoring and further analysis showed that the impacting distance of advanced abutment stress induced by mining in the strike of the working face along its central axis was the farthest, greater than 250 m (the face length is 220 m); it gradually decreased in the radial direction of the face from its central axis outward; the pressure peak was located within 24 m in the front of the mining coal wall; non-synchronous caving of the layered mudstone roof at the stope occurred. Comparison between vertical and horizontal stress increments indicated that the horizontal stress was much smaller than the vertical stress in the coal mass of mining side, while the latter’s magnitude determined the drastic degree of mine pressure manifestation. The study has been applied to determine the advanced support length of the working face and further provide a reliable basis to forecast such dynamic disasters as rock burst, coal and gas outburst, etc., as well as to design the asymmetric supports on both sides of a gateway.

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.