In order to effectively and efficiently obtain the sandstone-type uranium anomalous information in the concentration area of uranium ore, a 3-layer BP neural network has been constructed by the known uranium ore logging data based on the logging response characteristics of the sandstone-type uranium anomaly because of the nonlinear mapping and learning ability of BP neural network. The network was used to identify and extract information of the anomaly and mineralization layers based on the uranium ore logging data of a uranium ore area in the southern end of the Daqing placanticline of Songliao basin, and the identification results of model were compared with the known mineralized body information. The results showed that the recognition rate of BP neural network model is 86.55%, and the effect is better, the identification result of the mineralized layer is highly coincident with the information of the known ore body, and is closer to the abnormal distribution of the uranium ore than the conventional identification method of uranium ore anomaly. It can effectively and efficiently obtain the abnormal information of unknown drilling and reduce the error caused by human interpretation work, it has higher accuracy and obvious advantages. BP neural network has a great prospect in the applying of uranium exploration.