Enyuan Wang

Bayesian discriminant analysis for prediction of coal and gas outbursts and applicatio

Based on the principle of Bayesian discriminant analysis, we established a model of Bayesian discriminant analysis for predicting coal and gas outbursts. We selected five major indices which affect outbursts, i.e., initial speed of methane diffusion, a consistent coal coefficient, gas pressure, destructive style of coal and mining depth, as discriminating factors of the model. In our model, we divided the type of coal and gas outbursts into four grades regarded as four normal populations. We then obtained the corresponding discriminant functions through training a set of data from engineering examples as learning samples and evaluated their criteria by a back substitution method to verify the optimal properties of the model. Finally, we applied the model to the prediction of coal and gas outbursts in the Yunnan Enhong Mine. Our results coincided completely with the actual situation. These results show that a model of Bayesian discriminant analysis has excellent recognition performance, high prediction accuracy and a low error rate and is an effective method to predict coal and gas outbursts.

Correlation of electromagnetic radiation emitted from coal or rock to supporting resistance

Abstract More accurate forecasting of rock burst might be possible from observations of electromagnetic radiation emitted in the mine. We analyzed experimental observations and field data from the Muchengjian coal mine to study the relationship between electromagnetic radiation signal intensity and stress during the fracturing of coal, or rock, and samples under load. The results show that the signal intensity is positively correlated with stress. In addition, we investigated the change in the electromagnetic radiation intensity, the supporting resistance in a real coal mine environment, and the coal or rock stress in the mining area. The data analysis indicates that: 1) electromagnetic radiation intensity can accurately reflect the distribution of stress in the mining area; and, 2) there is a correlation between electromagnetic radiation intensity and supporting resistance. The research has some practical guiding significance for rock burst forecasting and for the prevention of accidents in coal mines.

Electromagnetic radiation early warning criterion of rock burst based on statistical theory

Abstract Rock bursts are serious natural disasters encountered worldwide in coal mining and rock engineering. In order to forecast rock bursts more effectively, a new rock burst forecasting index E , consisting of intensity and the number of pulses, is proposed, on the basis of abnormal characteristic symptoms of electromagnetic radiation (EMR) generated before rock bursts, combined with statistical theory. The index is distributed as a χ 2 distribution with 2 degrees of freedom, i.e., E ∼. Via this index, a quantitative comprehensive forecasting criterion of EMR was initially established. E values were calculated when the occurrence probability of the occurrence of a rock burst was 50%, 70% and 90%. Appropriate measures should be taken when using these values on the scene. Using EMR data collected in the Nanshan Mine of the Hegang mining area, we verified that the analytical result were consistent with actual situations. This index is of theoretical importance and as a reference for forecasting rock bursts in coal mines.

EMR: An effective method for monitoring and warning of rock burst hazard

Rock burst may cause serious casualties and property losses, and how to conduct effective monitoring and warning is the key to avoid this disaster. In this paper, we reviewed both the rock burst mechanism and the principle of using electromagnetic radiation (EMR) from coal rock to monitor and forewarn rock burst, and systematically studied EMR monitored data of 4 rock bursts of Qianqiu Coal Mine, Yima Coal Group, Co. Ltd. Results show that (1) Before rock burst occurrence, there is a breeding process for stress accumulation and energy concentration inside the coal rock mass subject to external stresses, which causes it to crack, emitting a large amount of EMR; when the EMR level reaches a certain intensity, which reveals that deformation and fracture inside the coal rock mass have become serious, rock burst may occur anytime and its necessary to implement an early warning. (2) Monitored EMR indicators such as its intensity and pulses amount are well and positively correlated before rock bursts occurs, generally showing a rising trend for more than 5 continuous days either slowly or dramatically, and the disaster bursts generally occurs at the lower level within 48 h after reaching its peak intensity. (3) The rank of EMR signals sensitive to rock burst in a descending order is maximum EMR intensity > rate of change in EMR intensity > maximum amount of EMR pulses > rate of change in the amount of EMR pulses.