Glass factory power prediction method and system based on BP neural network

The invention provides a BP neural network-based glass factory power prediction method and system, and the method comprises the steps: obtaining historical power load data, temperature and humidity before a prediction day, and the thickness and kiln temperature of a glass product as training samples; inputting the training sample into a BP neural network, and optimizing the BP neural network to obtain an optimized BP neural network model; and extracting electrical load data, temperature and humidity of the day before the prediction day, and the thickness and the kiln temperature of the glass product, and inputting the data and the temperature and the humidity into the optimized BP neural network model to predict the electrical load of the prediction day. The method has the beneficial effects that the electrical load of the glass factory is accurately predicted based on the BP neural network, so that the power demand of the superior power grid is determined according to the accurate electrical load prediction