Research on a Space-Time Continuous Sensing System for Overburden Deformation and Failure during Coal Mining.

Underground coal mining can cause the deformation, failure, and collapse of the overlying rock mass of a coal seam. If the mining design, monitoring, early warning, or emergency disposal are improper, in that case, it can often lead to mining disasters such as roof falls, water inrush, surface collapse, and ground fissures, seriously threatening the safety of mine engineering and the geological environment protection in mining areas. To ensure the intrinsic security of the entire coal mining process, aspace-time continuous sensing system of overburden deformation and failure was developed, which breaks through the limitations of traditional monitoring methods that characterize the evolution process of overlying rock deformation and ground subsidence. This paper summarizes the classification of typical overburden deformation and failure modes. It researches the space-time continuous sensing of rock-soil mass above the coal seam based on Distributed Fiber Optic Sensing (DFOS). A multi-range strain optical fiber sensing neural series from micron to meter was developed to achieve synchronous sensing of overburden separation, internal micro-cracks, and large rock mass deformation. The sensing cable-rock mass coupling test verified the reliability of the optical fiber monitoring data. The sensing neural network of overburden deformation was constructed using integrated optical fiber layout technology on the ground and underground. Different sensing nerves' performance and application effects in overburden deformation and failure monitoring were compared and analyzed with field monitoring examples. A physical model was used to carry out the experimental study on the overburden subsidence prediction during coal mining. The results showed that the optical fiber monitoring data were reliable and could be used to predict overburden subsidence. The reliability of the calculation model for overlying rock subsidence based on space-time continuous optical fiber sensing data was verified in the application of mining subsidence evaluation. A systematic review of the shortcomings of current overburden deformation observation technology during coal mining was conducted, and a space-time continuous sensing system for overburden deformation and failure was proposed. This system integrated sensing, transmission, processing, early warning, decision-making, and emergency response. Based on the fusion of multi-parameter sensing, multi-method transmission, multi-algorithm processing, and multi-threshold early warning, the system realized the real-time acquisition of space-time continuous information for the overburden above coal seams. This system utilizes long-term historical monitoring data from the research area for data mining and modeling, realizing the prediction and evaluation of the evolution process of overburden deformation as well as the potential for mining subsidence. This work provides a theoretical reference for the prevention and control of mining disasters and the environmental carrying capacity evaluation of coal development.

A probability prediction method for the classification of surrounding rock quality of tunnels with incomplete data using Bayesian networks.

The classification of surrounding rock quality is critical for the dynamic construction and design of tunnels. However, obtaining complete parameters for predicting the surrounding rock grades is always challenging in complex tunnel geological environment. In this study, a new method based on Bayesian networks is proposed to predict the probability for the classification of surrounding rock quality of tunnel with incomplete data. A database is collected with 286 cases in 10 tunnels, involving nine parameters: rock hardness, weathering degree, rock mass integrity, rock mass structure, structural plane integrity, in-situ stress, groundwater, rock basic quality, and surrounding rock level. Moreover, the Bayesian network structure is built using the collected database and quantitatively verified by strength analysis. Then, the accuracy, precision, recall, F-measure and receiver operating characteristic (ROC) curves are utilized for model evaluation. The average values of accuracy, precision, recall, F-measure, and area under the curve (AUC) are approximately 89.2%, 91%, 92%, 91%, and 0.98, respectively. These results indicate that the established classification model has high accuracy, even with small sample size and imbalanced samples. Ten additional sets of tunnel cases (incomplete data) are also used for verification. The results reveal that compared with the traditional Q-system (Q) and rock mass rating (RMR) classification methods, the proposed classification model has the lowest error rate and is capable of using incomplete data to predict sample results. Finally, sensitivity analysis suggests that the rock hardness and rock mass integrity have the strongest impact on the quality of tunnel surrounding rock. Overall, the findings of this study can serve as a useful reference for future rock mass quality evaluation in tunnels, underground powerhouses, slopes, etc.

UNetGE: A U-Net-Based Software at Automatic Grain Extraction for Image Analysis of the Grain Size and Shape Characteristics.

The shape and the size of grains in sediments and soils have a significant influence on their engineering properties. Image analysis of grain shape and size has been increasingly applied in geotechnical engineering to provide a quantitative statistical description for grain morphologies. The statistic robustness and the era of big data in geotechnical engineering require the quick and efficient acquirement of large data sets of grain morphologies. In the past publications, some semi-automation algorithms in extracting grains from images may cost tens of minutes. With the rapid development of deep learning networks applied to earth sciences, we develop UNetGE software that is based on the U-Net architecture-a fully convolutional network-to recognize and segregate grains from the matrix using the electron and optical microphotographs of rock and soil thin sections or the photographs of their hand specimen and outcrops. Resultantly, it shows that UNetGE can extract approximately 300~1300 grains in a few seconds to a few minutes and provide their morphologic parameters, which will ably assist with analyses on the engineering properties of sediments and soils (e.g., permeability, strength, and expansivity) and their hydraulic characteristics.

Multi-Classification of Complex Microseismic Waveforms Using Convolutional Neural Network: A Case Study in Tunnel Engineering.

Due to the complexity of the various waveforms of microseismic data, there are high requirements on the automatic multi-classification of such data; an accurate classification is conducive for further signal processing and stability analysis of surrounding rock masses. In this study, a microseismic multi-classification (MMC) model is proposed based on the short time Fourier transform (STFT) technology and convolutional neural network (CNN). The real and imaginary parts of the coefficients of microseismic data are inputted to the proposed model to generate three classes of targets. Compared with existing methods, the MMC has an optimal performance in multi-classification of microseismic data in terms of Precision, Recall, and F1-score, even when the waveform of a microseismic signal is similar to that of some special noise. Moreover, semisynthetic data constructed by clean microseismic data and noise are used to prove the low sensitivity of the MMC to noise. Microseismic data recorded under different geological conditions are also tested to prove the generality of the model, and a microseismic signal with Mw ≥ 0.2 can be detected with a high accuracy. The proposed method has great potential to be extended to the study of exploration seismology and earthquakes.

Characteristics and applications of ecological soil substrate for rocky slope vegetation in cold and high-altitude areas.

Ecological restoration of steep rocky slopes generated by road cutting is usually difficult especially, in the cold and high-altitude environment, which is unfavorable for the growth of vegetation. With the focus on slope vegetation, an ecological soil substrate, synthesized with polyacrylamide (PAM), carboxymethyl cellulose (CMC), and Fly ash (FA) as the main components, was developed for spray seeding on the rocky slopes in cold and high-altitude regions, to provide a favorable environment for vegetation growth. The compositional effect of individual compound addition on the growth of vegetation and substrate properties was investigated using an orthogonal array experimental design. Based on ANOVA and orthogonal analysis, an ecological soil substrate (PCF) with 400g/m3 PAM, 600g/m3 CMC, 1500g/m3 FA, and 50L/m3 of water was decided as the optimum PCF substrate. The optimum PCF substrate was then sprayed on a steep rocky slope in a cold and high-altitude region in Sichuan, China, for two years. The vegetation, as well as the physico-chemical properties, nutrient content, and mechanical properties of the field soil substrate, were examined over this duration. The field verification shows that the proposed PCF substrate is able to provide desirable nutrient contents and excellent physical and mechanical properties for vegetating the steep rocky slopes in cold and high-altitude areas.