硅单晶生长工艺参数建模及多目标优化  

Modeling and Multi Objective Optimization of Process Parameters for Silicon Single Crystal Growth

作　　者：黄伟超[1,2] 刘丁 

机构地区：[1]西安理工大学晶体生长设备及系统集成国家地方联合工程研究中心,西安710048 [2]陕西省复杂系统控制与智能信息处理重点实验室,西安710048

出　　处：《人工晶体学报》2017年第11期2095-2101,共7页Journal of Synthetic Crystals

基　　金：国家自然科学基金重点项目(61533014);国家重点基础研究发展计划(973计划)(2014CB360500)

摘　　要：为了获得满足高品质硅单晶体生长的工艺参数,一种计算流体动力学(computational fluid dynamics,CFD)方法、数据处理组合法(group method of data handing,GMDH)型神经网络和第二代非支配排序遗传算法II(nondominated sorting genetic algorithm II,NSGA-II)的混合策略被提出,并对Czochralski(Cz)法硅单晶生长进行建模和工艺参数的多目标优化。将包含了加热温度、晶转速度、埚转速度和提拉速度等四个设计变量的固液界面形变量h和缺陷评价准则V/G作为目标函数。通过CFD进行数值计算,获得GMDH训练所需要的样本,并建立目标函数多项式模型,最后利用NSGA-II得到满足了Pareto最优解的工艺参数。通过实际工程验证,证明了所提出的混合策略为获取晶体生长工艺参数提供了一种新的数值计算方法。In order to obtain higher quality silicon single crystal, this paper presents a hybrid strategy for modeling Czochralski silicon crystal growth and optimizing growth process parameters. This hybrid strategy includes computational fluid dynamics （CFD） method, data neural network based group method of data handing type, and non-dominated sorting genetic algorithm II （NSGA-II） ？ According to engineering experience and process requirement, the shape variables of solid-liquid interface h and defect evaluation criteria V/G , which containing four design variables that are the heating temperature, the crystal rotating speed, the crucible rotating speed and the pulling speed, are used as the objective functions. Through numerical calculation based on CFD software, the required samples are obtained for GMDH training. Ultimately, the process parameter satisfying the Pareto optimal solution are acquired by using NSGA-II. Tested by practical projects, it is proved that the proposed hybrid strategy provides a new numerical method for obtaining crystal growth parameters.

关 键 词：晶体生长 工艺参数优化 计算流体动力学 第二代非支配排序遗传算法 多目标优化 

分 类 号：O782[理学—晶体学]