A Deep Learning Based Dislocation Detection Method for Cylindrical Crystal Growth Process

Jun Zhang,Hua Liu,Jianwei Cao,Bo Jin,Weidong Zhu,Wei Li

doi:10.3390/app10217799

Abstract

For the single crystal furnace used in the photovoltaic industry, growth problems occur frequently due to dislocations during the shouldering and cylindrical growth steps of the Czochralski (CZ) crystal growth. Detecting the dislocation phenomenon in the cylindrical growth step is very important for entire automation of the CZ crystal furnace, since this process usually lasts for more than 48h. The irregular nature of different patterns of dislocation would impose a big challenge for a traditional machine vision-based detection method. As almost no publications have been dedicated to detecting this phenomenon, to address this issue, after analyzing the characteristics of the silicon ingot image of this process, this paper proposes a kind of deep learning-based dislocation detection method along with tracking strategy to simulate manual inspection. The model has a good detection effect whether there is occlusion or not, the experimental results show that the detection accuracy is 97.33%, and the inference speed is about 14.7 frames per second (FPS). It can achieve the purpose of reducing energy consumption and improving process automation by monitoring this process.

Highlights

CZ crystal growth is one of the most important techniques for manufacturing single crystalline silicon, which is the mainstay of the microelectronic and photovoltaic industries [1]
For the single crystal furnace used in the photovoltaic industry, growth problems occur frequently due to dislocations during the shouldering and cylindrical growth steps, which will seriously affect the quality of crystal silicon and the performance of the furnace and reduce the photoelectric conversion efficiency of solar cells
This paper proposes a kind of deep learning-based detection method

Summary

Introduction

CZ crystal growth is one of the most important techniques for manufacturing single crystalline silicon, which is the mainstay of the microelectronic and photovoltaic industries [1]. The schematic illustration of the single crystal furnace structure is shown, which mainly consists of five parts: furnace, crystal and crucible pulling and rotating mechanism, atmosphere and pressure control system, electrical system, and thermal field. The quartz crucible is used to store a polycrystalline silicon ingot and is heated by the surrounding high-purity graphite heater. By heating the crucible to a prescribed temperature, the raw material is melted and forms a pool of silicon melt in the crucible. As the seed is slowly pulled upwards while being rotated at a prescribed pulling and rotation speed, a cylindrical crystal ingot is grown. The gap distance between the melt surface and the bottom of the heat shield is referred to as the melt level. The cylindrical growth step is trying to maintain the diameter of the silicon ingot at a prescribed value during crystal growth

Objectives

Methods

Results

Discussion

Conclusion