A silicon rod growth rate prediction model in polysilicon reduction furnace is presented

Abstract

The invention discloses a silicon rod growth rate prediction model in a polycrystalline silicon reduction furnace, comprising a data acquisition and preprocessing module, which is used for acquiring data related to the silicon rod growth rate through a sensor and cleaning the acquired data; The data set screening module used for screening the data set after data collection and data cleaning of thedata collection module to obtain a training set and a test set; The Training and evaluating module, which is used for training the gradient lifting decision tree model and evaluating the model by using the average relative error and the eligibility rate; a prediction module, which is used for inputting the feature vector to be predicted; The prediction result module used for inputting the featurevector to be predicted into the prediction model and outputting the prediction result. The invention abandons the influence of complex chemical reaction on the growth rate in the traditional theoretical research, does not need to consider the complex chemical reaction, realizes the prediction of the growth rate of polysilicon, and provides guidance for improving the production efficiency and shortening the production cycle.

Description

technical field [0001] The invention relates to the technical field of polysilicon production technology, in particular to a model for estimating the growth rate of silicon rods in a polysilicon reduction furnace based on a weighted gray correlation improved GBDT regression algorithm. Background technique [0002] Polysilicon is widely used in photovoltaics, electronic devices and other equipment. With the depletion of petroleum and other energy sources, solar energy and other clean energy sources are widely concerned, resulting in an increasing demand for raw materials mainly polysilicon. Among the current polysilicon production processes, the most popular one is the improved Siemens process, which accounts for about 80% of the world's total silicon production. Most of the major polysilicon manufacturers in my country use the modified Siemens method to produce polysilicon. But at the same time, this process is also accompanied by disadvantages such as large energy loss an...

AI Technical Summary

Problems solved by technology

But at the same time, this process is also accompanied by disadvantages such as large energy loss and long production cycle.

[0003] And as far as the current domestic 24-rod reduction furnace is concerned, it takes about 120 hours for the silicon rods to fully grow to the required diameter. The long production cycle limits the production output and is accompanied by an increase in power consumption.

The production time of polysilicon is mainly related to the growth rate of silicon rods, but the growth rate of silicon rods is also subject to various process parameters, and the coupling between parameters is affected; at the same time, there are more than ten main and secondary chemical reactions involved in the reduction furnace. The reactions interact with each other, and the reaction kinetics are complex

The reaction rate is speculated from the reaction mechanism. At present, the reaction kinetics is mainly studied on the basis of theory and simulation. For the real-time performance of the site, the operability is not strong.

Too fast growth rate may cause the quality of silicon rods to be unguaranteed, prone to "popcorn", and too slow growth rate limits the production capacity of the reduction furnace and increases energy consumption; Under the premise of improving the growth rate, it is of great significance to evaluate the growth rate, improve production efficiency and reduce energy consumption

[0004] At present, most enterprises mainly observe the growth of silicon rods in the furnace through mirrors or detection devices, and then make corresponding adjustment parameters after obtaining part of the situation in the furnace. There is a lag problem; and for most silicon rods Theoretical research on rod growth rate is not very operable on site, and the reaction is complicated. It can only be analyzed offline, and cannot be evaluated on site.

Images