Thickness Distribution Prediction for Tectonically Deformed Coal with a Deep Belief Network: A Case Study

Thickness of tectonically deformed coal (TDC) has positive correlations with the susceptible gas outbursts in coal mines. To predict the TDC thickness of the coalbed, we proposed a prediction method using seismic attributes based on the deep belief network (DBN) and dimensionality reduction. Firstly, we built a DBN prediction model using the extracted attributes from a synthetic seismic section. Next, we transformed the possibly correlated seismic attributes into principal components through principal components analysis. Then, we compared the true TDC thickness with the predicted TDC thicknesses to evaluate the prediction accuracy of different models, i.e., a DBN model, a support vector machine model, and an extreme learning machine model. Finally, we used the DBN model to predict the TDC thickness of coalbed No. 8 in an operational coal mine based on synthetic experiments. Our studies showed that the predicted distribution of TDC thickness followed the regional characteristics of TDC development well and was positively correlated with the burial depth, coalbed thickness, and tectonic development. In summary, the proposed DBN model provided a reliable method for predicting TDC thickness and reducing gas outbursts in coal mine operations.

Productivity Evaluation of Coalbed Methane Well with Geophysical Logging-Derived Tectonically Deformed Coal

Tectonically deformed coal (TDC) has a significant influence on coalbed methane recovery. Well-logging is a reliable and efficient way to predict the development of TDCs for understanding the role of TDC on the productivity of coalbed methane (CBM) wells. However, there has been insufficient research regarding both the static physical properties and dynamic invasion of mud-filtrate related to TDCs. Therefore, a new TDC-detecting approach using two indicators of the relative physical properties and fluid attributes was proposed. Through the data normalization and optimization of correlation coefficients and factor analysis, five logs were chosen to construct the two indicators, and three types of TDC were recognized: I—undeformed or cataclastic; II—granulated; and III—mylonitized. It was found out that the identification error rate decreased from 30% to 15%. Furthermore, the thickness ratio of a well-preserved coal layer derived from TDC interpretation was adopted to correlate the gas production of a coal seam. An application in the Hancheng block demonstrated that the thickness ratio of 60% is an explicit threshold value to distinguish between high-yield well (>1000 m3/d) and low-yield one (<750 m3/d). The development of granulated and mylonitized coals mainly exerts negative influence on CBM well production.

Effect of moisture content on methane adsorption- and desorption-induced deformation of tectonically deformed coal

Intermolecular forces that act between moisture and the atoms of the coal structure have a significant influence on methane adsorption- and desorption-induced deformation in coal. After analyzing the porous characteristics and existing forms of moisture in coal, both the adsorption-induced swelling and the desorption-induced shrinkage deformation experiments were carried out under the conditions of varying moisture content, constant temperature, and variable equilibrium pressure. Both the swelling and shrinkage volumetric strains with different coal moisture contents were fitted by Langmuir-type equations in which the fitting coefficients were functions of the moisture content. It was found that there is a lag between the swelling curve and the corresponding shrinkage curve, and a variable known as the hysteresis rate was defined to illustrate this characteristic. A mathematical model of swelling and shrinkage deformation that considers the effect of moisture content was established based on the experimental results and analysis.