Model-Free Adaptive Diameter Control of Monocrystalline Silicon Based on Bayesian Parameter Optimization

Abstract

Abstract: The growth process of Czochralski silicon is related to multi-field and multi-phase coupling and complex physical and chemical changes. The fluctuations in process parameters are an important cause of uneven crystal diameter. This is significant research on how to achieve the control of process parameters to obtain an ideal and uniform crystal diameter. In this paper, after analyzing the instability and control effect degradation of the existing control method, a model-free adaptive control model based on Bayesian parameter optimization is presented to control the crystal diameter of the monocrystalline silicon growth process. Firstly, a model-free adaptive control model was established with crucible rising speed and heater power as control input parameters and crystal diameter as output parameters, and the stability of the algorithm was analyzed. Secondly, the control model was simulated and it is found that different super-parameter settings in the Czochralski silicon diameter control model will affect the number of iterations and the control effect. Finally, the value range of the hyper-parameter was optimized by Bayesian and the final simulation experiment was carried out. The results show that the model-free adaptive control optimized by the hyper-parameters is faster in calculation, less in iteration times, and the growth process parameters are controlled within the actual production requirements. Therefore, the model-free adaptive control based on Bayesian parameter optimization can effectively control the diameter of monocrystalline silicon, which has a practical application prospect combined with engineering background.

Key words: monocrystalline silicon, diameter control, model-free adaptive control, hyper-parameter, Bayesian parameter optimization

CLC Number:

TP23

LIN Guangwei, WANG Shan, ZHANG Xiya, PENG Xin, GAO Junwei, GAO Dedong. Model-Free Adaptive Diameter Control of Monocrystalline Silicon Based on Bayesian Parameter Optimization[J]. JOURNAL OF SYNTHETIC CRYSTALS, 2022, 51(2): 229-241.

References

[1] GOETZBERGER A, KNOBLOCH J, VOß B. Crystalline silicon solar cells[M]. Chichester, UK: John Wiley & Sons, Ltd, 2014.
[2] 尹建华,李志伟.半导体硅材料基础[M].北京:化学工业出版社,2009:97-107.
YIN J H, LI Z W. Fundamentals of semiconductor silicon materials[M]. Beijing: Chemical Industry Press, 2009: 97-107(in Chinese).
[3] BROWN R A. Theory of transport processes in single crystal growth from the melt[J]. AIChE Journal, 1988, 34(6): 881-911.
[4] GEVELBER M A, STEPHANOPOULOS G, WARGO M J. Dynamics and control of the Czochralski process Ⅱ. Objectives and control structure design[J]. Journal of Crystal Growth, 1988, 91(1/2): 199-217.
[5] GEVELBER M A. Dynamics and control of the Czochralski process Ⅳ. Control structure design for interface shape control and performance evaluation[J]. Journal of Crystal Growth, 1994, 139(3/4): 286-301.
[6] GALAZKA Z, WILKE H. Heat transfer and fluid flow during growth of Y₃Al₅O₁₂ single crystals using the czochralski method[J]. Crystal Research and Technology, 2000, 35(11/12): 1263-1278.
[7] 刘丁.单晶硅生长的建模与控制[M].北京:科学出版社, 2015: 241-252.
LIU D. Modeling and control of Czochralski silicon single crystal growth[M]. Beijing: Science Press, 2015: 241-252(in Chinese).
[8] 张晶,潘亚妮,刘丁,等.基于响应面法的直拉硅单晶生长工艺参数优化方法[J].人工晶体学报,2018,47(12):2429-2435.
ZHANG J, PAN Y N, LIU D, et al. Optimization of cz silicon monocrystal growth process parameters based on response surface method[J]. Journal of Synthetic Crystals, 2018, 47(12): 2429-2435(in Chinese).
[9] 刘丁,赵小国,赵跃.直拉硅单晶生长过程建模与控制研究综述[J].控制理论与应用,2017,34(1):1-12.
LIU D, ZHAO X G, ZHAO Y. A review of growth process modeling and control of Czochralski silicon single crystal[J]. Control Theory & Applications, 2017, 34(1): 1-12(in Chinese).
[10] ARMAOU A, CHRISTOFIDES P D. Crystal temperature control in the Czochralski crystal growth process[J]. AIChE Journal, 2001, 47(1): 79-106.
[11] ABDOLLAHI J, IZADI M, DUBLJEVIC S. Model predictive temperature tracking in crystal growth processes[J]. Computers & Chemical Engineering, 2014, 71: 323-330.
[12] ABDOLLAHI J, IZADI M, DUBLJEVIC S. Temperature distribution reconstruction in Czochralski crystal growth process[J]. AIChE Journal, 2014, 60(8): 2839-2852.
[13] WINKLER J, NEUBERT M, RUDOLPH J. Nonlinear model-based control of the Czochralski process I: motivation, modeling and feedback controller design[J]. Journal of Crystal Growth, 2010, 312(7): 1005-1018.
[14] WINKLER J, NEUBERT M, RUDOLPH J. Nonlinear model-based control of the Czochralski process Ⅱ: reconstruction of crystal radius and growth rate from the weighing signal[J]. Journal of Crystal Growth, 2010, 312(7): 1019-1028.
[15] NEUBERT M, WINKLER J. Nonlinear model-based control of the Czochralski process Ⅲ: proper choice of manipulated variables and controller parameter scheduling[J]. Journal of Crystal Growth, 2012, 360: 3-11.
[16] NEUBERT M, WINKLER J. Nonlinear model-based control of the Czochralski process Ⅳ: feedforward control and its interpretation from the crystal grower′s view[J]. Journal of Crystal Growth, 2014, 404: 210-222.
[17] 万银.基于有限元模型的CZ法硅单晶温度与直径跟踪控制[D].西安:西安理工大学,2019.
WAN Y. Temperature and diameter tracking control of CZ method single crystal based on finete element model[D]. Xi'an: Xi'an University of Technology, 2019(in Chinese).
[18] 张俊,林勇刚,高宇,等.300 mm单晶硅生长过程中直径的功率控制方法[J].稀有金属,2021,45(6):687-694.
ZHANG J, LIN Y G, GAO Y, et al. Diameter control by heater power during 300 mm silicon crystal growth[J]. Chinese Journal of Rare Metals, 2021, 45(6): 687-694(in Chinese).
[19] 段伟锋.硅单晶等径阶段直径模型辨识与控制研究[D].西安:西安理工大学,2017.
DUAN W F. Model identification and control of silicon single crystal diameter for constant-diameter growth stage[D]. Xi'an: Xi'an University of Technology, 2017(in Chinese).
[20] 项森伟.高温单晶硅液位和直径视觉检测关键技术及应用研究[D].杭州:浙江大学,2018.
XIANG S W. Research on the key technology and application of high temperature monocrystalline silicon liquid level and diameter detection by vision[D]. Hangzhou: Zhejiang University, 2018(in Chinese).
[21] 乔朝晖.无味卡尔曼滤波在直拉法单晶硅直径控制中的应用研究[D].兰州:兰州大学,2015.
QIAO C H. Research of applying UKF in crystal diameter control of czochralski process[D]. Lanzhou: Lanzhou University, 2015(in Chinese).
[22] 张晶,刘丁,杜燕军.直拉硅单晶非均匀相变温度场最优控制[J].控制理论与应用,2021,38(1):44-52.
ZHANG J, LIU D, DU Y J. Optimal control for heterogeneous phase transition temperature field of Czochralski monocrystalline silicon[J]. Control Theory & Applications, 2021, 38(1): 44-52(in Chinese).
[23] 姜舰,邓树军,戴小林,等.大直径直拉硅单晶等径的PID参数优化[J].稀有金属,2010,34(6):945-949.
JIANG J, DENG S J, DAI X L, et al. Optimization of PID control parameters for large diameter silicon crystal growth[J]. Chinese Journal of Rare Metals, 2010, 34(6): 945-949(in Chinese).
[24] 侯忠生.基于无模型学习的非线性系统自适应控制[D].沈阳:东北大学, 1994.
HOU Z S. Parameter identification, adaptive control and modelless learning adaptive control for nonlinear systems[D]. Shenyang: Northeastern University, 1994(in Chinese).
[25] HOU Z S, WANG Z. From model-based control to data-driven control: survey, classification and perspective[J]. Information Sciences, 2013, 235: 3-35.
[26] HOU Z S, CHI R H, GAO H J. An overview of dynamic-linearization-based data-driven control and applications[J]. IEEE Transactions on Industrial Electronics, 2017, 64(5): 4076-4090.
[27] HOU Z S, JIN S T. A novel data-driven control approach for a class of discrete-time nonlinear systems[J]. IEEE Transactions on Control Systems Technology, 2011, 19(6): 1549-1558.
[28] 熊双双.无模型自适应控制的稳定性分析及在多智能体系统中的应用[D].北京:北京交通大学,2020.
XIONG S S. Stability analysis of model free adaptive control with applications in multi-agent systems[D]. Beijing: Beijing Jiaotong University, 2020(in Chinese).
[29] 宋杨.船舶减摇无模型自适应控制技术研究[D].大连:大连理工大学,2013.
SONG Y. Research on ship anti-rolling control techniques with model free learning adaptive control method[D]. Dalian, China: Dalian University of Technology, 2013(in Chinese).
[30] 宋泽雨,李国庆,刘凌轩.一种新的无模型自适应控制模型参数整定方法[J].化工学报,2019,70(9):3430-3440.
SONG Z Y, LI G Q, LIU L X. New determination method of parameters for model-free adaptive control[J]. CIESC Journal, 2019, 70(9): 3430-3440(in Chinese).
[31] 杨欢,吴震,王燚,等.侧信道多层感知器攻击中基于贝叶斯优化的超参数寻优[J].计算机应用与软件,2021,38(5): 323-330.
YANG H, WU Z, WANG Y, et al. Hyper-parameters optimization in side-channel attack of multilayer perceptron based on byesian optimization[J]. Computer Applications and Software, 2021, 38(5): 323-330(in Chinese).
[32] 吴浩楠.超参数自动调优算法研究[D].哈尔滨:哈尔滨工业大学,2020.
WU H N. Research on automatic hyper-parameter tuning algorithm[D]. Harbin: Harbin Institute of Technology, 2020(in Chinese).
[33] KLEIN A, FALKNER S, BARTELS S, et al. Fast bayesian optimization of machine learning hyperparameters on large datasets[J]. Machine Learning, 2016, arXiv: 1605.07079.
[34] WANG X, EISSELER R, MOEHRING H C. Prediction and optimization of machining results and parameters in drilling by using Bayesian networks[J]. Production Engineering, 2020, 14(3): 373-383.