At present, the detection of mixing uniformity in glass furnace batching system is mainly realized by artificial detection. However, this method is time-consuming and laborious, and there are some risks. For the problem of mixing uniformity detection, the nonlinear relation between the actual weight value and the mixing uniformity is established by the BP neural network, which can predict the mixing uniformity of ingredients. In order to solve the problem of large error in the prediction value of the network, a genetic algorithm is used to optimize the weights and thresholds of the network. Taking the horseshoe flame glass furnace of the Yellow River brewery in Lanzhou as an example, the evolutionary network can achieve the prediction accuracy of the mixing uniformity of the mixture required by the factory.