基于MIC的Cz单晶硅放肩阶段关键特征参数辨识

赵华东; 翟晓彤; 田增国; 李欣鸽

人工晶体学报, 2020, 49 (4): 607, 网络出版: 2020-06-15

基于MIC的Cz单晶硅放肩阶段关键特征参数辨识

Identification of Key Characteristic Parameters of Cz-Si Monocrystal during Shoulder Growth Process Based on MIC

论文大纲

赵华东 ¹翟晓彤 ¹田增国 ^2,*李欣鸽 ²

作者单位

¹ 郑州大学机械与动力工程学院，郑州 450001

² 郑州大学物理学院，郑州 450001

摘要

直拉单晶硅生长过程中放肩阶段常由于断棱的出现导致无法顺利进入等径生长。为研究影响断棱的关键特征参数，提出采用最大互信息系数法(MIC)辨识直拉单晶硅放肩阶段关键特征参数。分别采用最大互信息系数法(MIC)、层次分析法(AHP)计算特征参数与放肩断棱的相关系数，按照降序依次提取前k项直至全部特征参数作为输入参数，在逻辑斯蒂回归模型进行放肩断棱预测评估。结果表明，采用MIC提取特征参数的前13项特征作为输入参数时，模型的准确度最高；且采用MIC法在预测精度上优于AHP法。

Abstract

The crystal often cannot smoothly enter the body growth process from the shoulder growth process during crowning growth of Cz Silicon monocrystal growth due to the appearance of Broken Edge. To study the key characteristic parameters that affect Broken Edge, a method based on the Maximum Mutual Information(MIC) to identify the key characteristic parameters of the shoulder growth process of Cz-Si monocrystal growth were proposed. The correlation coefficients of the characteristic parameters to a Broken Edge problem each was calculated by the MIC method and the analytic hierarchy process (AHP). Then the first k terms were sequentially extracted in descending order until all feature parameters were used as input parameters for the Logistic Regression model to predict probability of Broken Edge. The results obtained show the accuracy of the model is the highest when the first 13 features of MIC extracted feature parameters were used as input parameters; and the MIC method is superior to the AHP method in prediction accuracy.

参考文献

[1] Muller G. Review:the czochralski method-where we are 90 years after jan czochralski invention[J].Crystal Research and Technology,2007,42(12):1150-1161.

[2] Ammon W V. Crystal growth-fundamentals of melt growth[J].Elsevier Amsterdam,2004:239-270.

[3] Shiraishi Y. Prediction of solid-liquid interface shape during czochralski growth using experimental and global simulation[J].Journal of Crystal Growth,2004,266:282-314.

[4] 裴志军,纪秀峰,刘峰.4英寸<111>硅单晶制备中断棱与掉苞问题[J].半导体杂质,1998,23(3):20-23.

[5] 董建明,张波,刘进,等.直拉法硅单晶生长中断棱与掉苞问题的探讨[J].材料导报,2013,27(21):157-159.

[6] 张晶,刘丁,赵跃,等.直拉硅单晶放肩过程的有限元数值模拟与控制参数研究[J].半导体杂质,2013,42(1):58-64.

[7] Li J L, Koichi Kakimoto. 3D global analysis of Cz-si growth in a transverse magnetic field with various crystal growth[J].Crystal Growth,2005,282:521-526.

[8] Choudhary A K, Harding J A, Tiwari M K. Data Mining in manufacturing:a review based on the kind of knowledge[J].Journal of Intelligent Manufacturing,2009,20(5):501-521.

[9] 郭园园.基于互信息的信息基因选择算法研究[D].湖南:湘潭大学,2018.

[10] Reshef D N, Reshef Y A, Finucane H K, et al. Detecting novel associations in large data sets [J].Science,2011,334(6062):1518-1524.

[11] SHAO F B，LI K P，et al. Railway accidents analysis based on the improved algorithm of the maximal information coefficient[J].Intelligent Data Analysis,2016,20(3):597-613.

[12] Sagl G, Blaschke T, Beinat E, et al. Ubiquitous geo-sensing for context-aware analysis:exploring relationships between environmental and human dynamic[J].Sensors,2012,12(7):9800-9822.

[13] Eiler A, Zaremba-Niedzwied-Zka K, Martin-Ez-Carcia M, et al. Productivity and salinity structuring of the microplankton revealed by comparative fresh-water metagenomic[J].Environmental Micro-biology,2014,16(9):2682-698.

[14] Acharya V, Sharma S K, Gupta S K, et al. Analyzing the factors in industrial automation using analytic hierarchy process[J].Comput Electr. Eng.,2018,71:877-886.

[15] Agapova M, Bresnahan B W, Linnau K F, et al. Using the analytic hierarchy process for prioritizing imaging tests in diagnosis of suspected appendicitis[J].Acad Radiol,2017,24(5):530-537.

赵华东, 翟晓彤, 田增国, 李欣鸽. 基于MIC的Cz单晶硅放肩阶段关键特征参数辨识[J]. 人工晶体学报, 2020, 49(4): 607. ZHAO Huadong, ZHAI Xiaotong, TIAN Zengguo, LI Xinge. Identification of Key Characteristic Parameters of Cz-Si Monocrystal during Shoulder Growth Process Based on MIC[J]. Journal of Synthetic Crystals, 2020, 49(4): 607.

基于MIC的Cz单晶硅放肩阶段关键特征参数辨识

关于本站 Cookie 的使用提示

全站搜索

基于MIC的Cz单晶硅放肩阶段关键特征参数辨识

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索