Prediction model of molten iron endpoint temperature in AOD furnace based on RBF neural network

Abstract

According to Jilin Ferroalloy Factory 10-ton AOD furnace actual smelting condition, analyzes the impact factor of AOD furnace molten iron endpoint temperature, by optimizing the neural network connection weights and structure, design prediction model of molten iron endpoint temperature based on RBF neural network, using LM algorithm and 50 furnaces actual production data to train the model, and predicts another 50 furnaces molten iron temperature, Result shows that prediction model of molten iron endpoint temperature based on RBF neural network has a high accuracy, when the error of endpoint temperature is ± 12 °C, hit rate of temperature is 82.4%.