Monocrystalline silicon smelting furnace crystal growth diameter prediction method

The invention relates to a method for predicting the crystal growth diameter of a monocrystalline silicon smelting furnace. The method is based on a PSO optimized KNN algorithm. The method has the advantages that for the diameter control problem in the monocrystalline silicon growth process, a large amount of historical growth data of different melting furnaces are utilized, and different growth stages are divided into different data sets; in order to eliminate the influence of overlarge numerical difference of different data types on the weight, a normal normalization method is adopted to carry out data enhancement. And inputting a KNN regression model to optimize a weighted weight. After training is finished, crystal growth data can be input into the regression model in the application stage, the growth diameter under historical similar parameters is given, and the crystal growth diameter at the next moment is predicted. A PSO-optimized KNN regression calculation model with a weight is utilized to realize a