Research On The Height Of Water Flowing Fractured Zone Based On Fuzzy Clustering Analysis And Neural Network

The exploitation and utilization of coal resources have made great contributions to the economic development of our country,but at the same time,it has brought a series of problems.For example,the current environmental problems are becoming more and more serious.A series of environmental problems such as surface subsidence,the circulation,pollution and waste of surface water are urgently needed to be solved.And as we all know,coal mining is a high-risk industry.Mine water-disaster seriously threatens the life safety of miners.In addition,In the past,unreasonable exploitation of coal resources lead to a large waste of coal resources.Therefore,it is imperative to rationally determine the upper mining limit and improve the recycle rate of coal resources.We look for reasons related to the above problems,and find that the height of water flowing fractured zone is closely related to it.So the determination of the water flowing fractured zone have a great significance to solve the above problems.However,there are many influencing factors on the height of water flowing fractured zone.At present,most of the height values are getted by the empirical formulas and the errors are usually larger.On the other hand It is difficult to directly study the height of water flowing fractured zone.Based on these,this paper proposes to study the heights of water flowing fractured zone through the alreday acquired information of water flowing fractured zone.In this paper firstly,the fuzzy clustering analysis is designed.The algorithm is used to classify 57 working face date.And accroding to the membership between 3 working face date(predictive samples)from Gu Bei Mine and classification of 57 working face date,we can get the classification of 3 predictive samples.In other words,the redundant data in the predictive samples can be removed by this algorithm.Then according to the characteristics of each classification to establish the correspon-ding double-precision artificial neural network model.Finally,the classification data are imported into their respective artificial neural networks model,and then get the 3 predictive samples height of water flowing fractured zone.Studying the height of water flowing fractured zone through the alreday acquired information of water flowing fractured zone,which provided a idea for studying the height of water flowing fractured zone.In this paper,the fuzzy clustering analysis and the artificial neural network model are combined to improve the quality of the training samples in the artificial neural network model.On the other hand,the corresponding artificial neural network model can be established according to the characteristics of each classification.Therefore,the predictive values of the height of water flowing fractured zone obtained by the combined model is more objective and true.In addition,compared with the traditional artificial neural network model,the double-precision artificial neural network model established in this paper further improves the prediction accuracy of the combined model.After verification of multiple verification formulas,the accuracy of the height of water flowing fractured zone value obtained from the combined model is high,and the prediction result is scientific and credible.