Polycrystalline silicon ingot casting quality prediction method and system based on batching data

Abstract

The invention relates to a polycrystalline silicon ingot casting quality prediction method and system based on batching data. The method comprises the following steps: acquiring batching data of a polycrystalline silicon ingot; preprocessing the batching data; wherein the preprocessing comprises the steps of performing data cleaning and deleting data with missing numerical values; performing dimension reduction processing on the preprocessed batching data by using a diffusion mapping algorithm; constructing a support vector data description model by using the batching data subjected to dimension reduction processing in a set proportion; and utilizing the trained support vector data description model to carry out quality prediction classification on the batching data after dimension reduction processing to obtain a product quality prediction classification result. According to the polycrystalline silicon ingot casting quality prediction method and system based on the burdening data, prediction of the polycrystalline silicon ingot casting quality can be rapidly and accurately achieved with low cost.

Description

technical field [0001] The invention relates to the field of polycrystalline silicon ingot quality prediction, in particular to a polycrystalline silicon ingot quality prediction method and system based on batching data. Background technique [0002] Polycrystalline silicon is a form of elemental silicon. When molten elemental silicon solidifies under supercooled conditions, silicon atoms are arranged in the form of diamond lattices to form many crystal nuclei. If these nuclei grow into crystal grains with different crystal plane orientations, these The grains combine to crystallize into polysilicon. A complete cycle of polysilicon ingot mainly includes: spraying and charging, pre-ingot inspection, ingot running process, prescription, silicon wafer processing and silicon wafer inspection and other technological processes. [0003] In the process of polysilicon ingot casting, its state can be described in the form of actual measured physical quantities or mathematical statis...

AI Technical Summary

Problems solved by technology

[0010] It can be seen that the existing methods cannot realize the effective prediction of the quality of polysilicon ingots quickly, accurately and at low cost.

Images