Research on component analysis and identification based on clustering and prediction model

Abstract

To better study the ancient relics of glass types and content of chemical composition, this article first USES no sequence grey prediction model to predict and distribution rules of cultural relics of the weathering before chemical component content, and then USES the K Means clustering will classify glass, finally set up the BP neural network model, based on the experimental data respectively set up the training set and validation set, Predicting the type of glass artifacts. It solves the problem of composition analysis and identification of glass cultural relics.