Abstract：For in place leaching of fragmented uranium ore by blasting，the ore heap is a loose fragmented medium，whose particle sizes follow the Rosin-Rammler distribution. The gas seepage in the medium is influenced by characteristic particle size，particle size distribution index and porosity simultaneously. To study the influence，seven samples are compound with different particle size gradations based on Rosin-Rammler distribution. The laws of gas seepage in seven samples are studied based on self-developed apparatus. On the basis of the test results，the adaptive neuro-fuzzy inference system(ANFIS) model for predicting seepage ratio and inertial coefficient is established using the adaptive neuro-fuzzy inference system based on characteristic particle size，particle size distribution index and porosity. The research results show that gas seepage in fragmented medium does not follow Darcy¢s law but follows Darcy-Forchheimer¢s law. Therefore，the ANFIS model provides predictions with high accuracy，which proves to be a new approach for estimation of permeability and inertial coefficient.
