Research On Coal Miners' Safety Behavior Evaluation And Its Pre-warning

As we all know,energy issues related to the lifeblood of the national economy."13th Five-Year" national planning pointed out that building green coal energy imperative.However,according to the China coal industry yearbook data show that nearly twenty years of coal mine accidents accounted for about 25%of the industrial and mining enterprises in the country,the number of deaths accounted for about 40%.It goes without saying that the cause of these accidents can not be determined from a single level.Local government supervision is not strict,enterprise economic interests;security awareness is low,the coal miners' safety skills shortage,poor operating environment,safety management and other factors in a certain extent,leading to frequent mining accidents.But in the final analysis stems from the unsafe behavior of employees.Therefore,it is an urgent problem for the government and enterprise decision-makers to identify and monitor the safety behavior of coal mine staff in the complex environment.In this paper,the safety behavior of front-line employees in coal mine is selected as the research object.Based on the complexity and systematization of coal mine safety production,through the study of typical coal mine accidents from 2001 to 2016 and the domestic and foreign periodical literature,this paper summarizes the factors affecting the safety behavior of coal miners.With the help of coal mine accident analysis,field investigation,questionnaire survey and behavioral event interview,the reliability and scientific of the influencing factors were verified.On the basis of screening the index of safety behavior of coal mine workers,the indexes are optimized and analyzed.What's more,index quantitative and hierarchy.And then build a practical and effective evaluation index system of coal mine workers' safety behavior.In addition,the information entropy method is used to analyze and calculate the index weight of each factor.Then,with the help of self-learning and adaptive ability of BP neural network,the 10 known samples of Huainan mining group and Henan Pingdingshan coal mining group under the jurisdiction can achieve the learning and acquisition of expert thinking.Afterwards,the trained network is used to simulate the samples which have not been measured,which can effectively reduce the influence of human factors in safety evaluation.In addition,through the training of the network can also get the corresponding weights of the indicators,and then according to the value of the indicators of the value of the coal mine staff safety behavior.On the basis of previous studies,to further clarify the behavior of coal mine staff safety warning mechanism,namely:pre-warning index selection,pre-warning system,single index warning interval and comprehensive index warning interval.On this basis,the BP neural network and BP neural network improved by genetic algorithm are compared and analyzed.The results show that the convergence speed and accuracy of the improved BP neural network is more accurate and effective.Finally,based on the pre-warning analysis and countermeasures,we hope to achieve the good operation of the coal mine safety pre-warning management mode and the effective integrated control of employee safety behavior.