Research Of Causal Chain Of Coal Mine Gas Accident Based On Association Rule Mining

In recent years, despite the remarkable effort performed at different levels to achieve a safety production of coal mine, such as the input of capital, the innovative trend in technology and the implementing of safety-related regulations, the occurrence of accidents and incidents is still prevalent worldwide. Furthermore, since gas accident is the most serious and common accident in coalmine. Consequently, it is significant to study the formation mechanism of gas accidents and the regulations to prevent them. At present, causal models of coalmine accident are almost established from direct, remote and root causes, however, the “big date” of coal mine accidents have not been made full uses.In order to effectively use the “big data” of coalmine accidents to analyze the potential causal mechanism of the accidents, the coalmine causal model include the factors of environment, equipment and human is proposed in this work. Furthermore, based on the causal model, by analyzing the accident investigation reports and transforming the text reports to related data, the coalmine accident database is finally established. Then, JAVA is used to mining the causal chain of gas accidents in the established database system, and the maximum frequent item sets is obtained. Furthermore, the relationships among these causal factors are analyzed and the causal chain of coalmine gas accidents is finally obtained. The results show that the violation of the regulations is the immediate causal factor for coalmine accidents, simultaneously, the inefficient implementation of regulation is the core causal factor for these accidents. Finally, the causal chain of gas accident can be restrained by the way of efficient implementation of regulation and rules. As a result, the occurrence probability of coalmine gas accident can be largely reduced.