Evaluate On The Stability Of Cavitary Gob Area In North Of Shaanix Province

A mass of gob area were produced when the mineral resources was excavated for theneed of development in north of Shaanxi Province which has large numbers of mineralresources. The cavitary gob area which its part of excavation is empty has the worst instabilityand dangerous among gob area. A series of geologic hazard which be triggered by cavitarygob area have features which were sudden, large-scale, severelyimpair and so on. Therefore,accurate evaluating the stability of cavitary gob areas has stronger meaning of disasterprevention and reduction.In this paper, the Taolaowusu Coal Gob Area was taken as example, its mining andgeological background was analysed and the characteristics of gob area which is cavitary wassummarized. The form of movement and destruction of wall rock in gob area and surface ongob area was concluded and their individual characteristics were analyzed,combined with theinstantaneous strength theory of rock and long-term strength theory, the general mechanism ofrock deformation and failure was concluded. Through the analysed the mechanism of rockdeformation and failure, restored the process of rock failure to stabilize, compared theadvantages and disadvantages of tunnel stability theory, the five kinds of factors whichaffected stability of gob area were concluded, they are geological factors, environmentalfactors, hydrological factors, gob geometrical parameters and time factors.The theory of BP neural network which is non-linear was introduced and the model ofthree layers BP neural network for evaluating the stability of cavitary gob area through itsadvantage which is non-linear mapping. The factors which are more important to the stability of cavitary gob area were choosen as input neurons of the model of BP neural network and theresults of stability of gob area were choosen as output neurons. Then the number of middleneurons were defined by trial computing with the golden section method and the empiricalmethod. At last, the structure of BP neural network model was defined as 11—22—4, Themodel which had the best ability to distinguish was made by training and amending withsamples of cavitary gob area which were collected. Then the model was used to evaluate thestability of Taolaowusu coal gob area and the result was"instability".The roof and floor of coal seam model of Taolaowusu coal gob area were built throughthe Finite difference software FLAC3D, then the process of excavating coal seam and loadingroadbed when the gob area had not managed were simulated under the initial stress field andthe displacement, stress and plastic developments of model s were observed. According to thetheory of rock strength, the results which the roof and floor of coal seam is safe and the coalblock is in danger when the compressive stress of coal block tended to be close to strengthenof coal blcok. Especially in that case which the gob area had not managed,the coal blockwould be destoryed instantaneously when loading roadbed on the floor. Therefore, theevaluated result of numerical experimentation was"instability"too.