Abstract: The construction and application of underground ponding goaf in coal mine provide important guarantee for underground production and mining and surface industrial water. The mine pays more attention to the safe operation performance of artificial waterproof sealing. For providing reliable monitoring scheme and safety evaluation technical means, taking 3^# waterproof sealing wall in 31205 ponding goaf of Shigetai Coal Mine as the research object, the monitoring scheme for surface strain gauge, borehole stress gauge and osmometer is designed, and the surface strain gauge B1, B3 and borehole stress gauge LY are used as the input matrix, and the osmometer LS1 is used as the output matrix. The GRNN model (generalized neural network) is introduced, and the network training and data prediction evaluation are conducted using the ten fold cross validation method and cycle iteration logic. The best smoothing factor is 0.2, and 97% of the absolute error of seepage pressure prediction results under this condition is less than 0.01; at the same time, compared with BP neural network model, GRNN model is superior to BP model. PNN model (probabilistic neural network) is introduced to verify the classification of 100 data in 10 grades of GRNN model classification evaluation results, and the accuracy of evaluation samples is 96.7%. The results show that GRNN model can accurately predict the seepage pressure monitoring data, and the accuracy of GRNN model is higher than that of BP model; the evaluation grade predicted by GRNN model can still be effectively evaluated and verified by using PNN model.