The coal blending mode of the current railroad rapid quantitative loading system is simple. The coal blending accuracy is low the speed is slow. Due to the fluctuation of coal type and coal quality, coal blending is an optimization problem under uncertain conditions, which cannot be solved by a traditional linear programming model. This paper focused on the fast quantitative coal blending method based on BP neural network to model and analyzed the materials and optimize the coal blending mode. The effects of the BP neural network and the number of hidden layer nodes on the prediction result were analyzed. Based on the traditional fixed dosage mode, the neural network was introduced into the dosage control algorithm, and the fast quantitative intelligent control method based on BP neural network was established to optimize the dosage control process, which improved the coal blending accuracy while accelerating the speed of dosage and coal, and effectively improved the efficiency of loading system in mining enterprises.