Study On Safety Rating Of Open Pit Mine Based On Production Risk

The occurrence of open-pit mine safety accidents will not only cause great economic losses to enterprises but also cause irreversible injuries to staff.In order to reduce the probability of production safety accidents in open-pit mines and promote the upgrade of the safety management system of open-pit enterprises,it is necessary to construct a more scientific and reasonable evaluation model,carry out quantitative analysis on the production risk of open-pit mines,propose targeted measures,provide more comprehensive decision-making information for enterprise managers,and improve the level of open-pit safety production.Text mining,Fuzzy Interpretative Structural Modeling,Analytic Network Process,grey-weighted cluster analysis,radial basis neural network,and other methods to construct the open-pit mine production risk assessment model,sort out the complicated and chaotic influence relationship among risk factors,reveal the nature of risk formation,through the combination of grey clustering model and genetic algorithm optimized RBF neural network to realize the quantification of open-pit production risk.It is verified by the practical application of A open-pit iron mine in Liaoning Province.The research results obtained are as follows:(1)Through text mining,data mining,and literature analysis,extract the risk factors affecting the safety production of open-pit mines from the collected data;Combined with the results of word frequency analysis and word frequency-inverse document frequency(TF-IDF),from the four aspects of equipment process risk,personnel safety risk,organizational management risk,and environmental safety risk,extract the production risk factors of open pit mine,build the open pit production risk evaluation index system.(2)Fuzzy interpretation structure model is used to sort out the intricate causal relationship between open pit production risks,find out the deep root cause of open pit production risks and the driving force factors and dependence factors of system risks,and provide an intuitive visual risk analysis method for enterprise managers.(3)On the basis of the relationship between the factors analyzed by the fuzzy interpretation structure model,the network structure relationship of the network analytic hierarchy process is constructed,the importance of the risk factors is evaluated by the Delphi method,and the weight of each risk is calculated by the evaluation results.After determining the weight,the quantitative value of the specific risk is calculated by the grey-weighted clustering analysis method.To realize the change of surface mine production risk from qualitative to quantitative.(4)Taking an open-pit iron mine in Liaoning Province as an example,the GA-RBF neural network is constructed and trained with grey clustering model data as input and output.After determining the optimal RBF parameters through a genetic algorithm,the performance of the trained neural network is evaluated and the risk level of an open-pit iron mine is evaluated.The evaluation results were compared with the results of the grey clustering model to verify the validity of the quantified risk values.At the same time,according to the evaluation results,the thesis puts forward the targeted improvement suggestions for the mine and provides a reference for the safety production of an open-pit mine.