Automatic optimization of measurement accuracy through advanced machine learning techniques

    公开(公告)号:US11380594B2

    公开(公告)日:2022-07-05

    申请号:US15903693

    申请日:2018-02-23

    Abstract: Machine learning techniques are used to predict values of fixed parameters when given reference values of critical parameters. For example, a neural network can be trained based on one or more critical parameters and a low-dimensional real-valued vector associated with a spectrum, such as a spectroscopic ellipsometry spectrum or a specular reflectance spectrum. Another neural network can map the low-dimensional real-valued vector. When using two neural networks, one neural network can be trained to map the spectra to the low-dimensional real-valued vector. Another neural network can be trained to predict the fixed parameter based on the critical parameters and the low-dimensional real-valued vector from the other neural network.

    Polygon-based geometry classification for semiconductor mask inspection

    公开(公告)号:US10140698B2

    公开(公告)日:2018-11-27

    申请号:US15230836

    申请日:2016-08-08

    Abstract: Disclosed are methods and apparatus for providing feature classification for inspection of a photolithographic mask. A design database for fabrication of a mask includes polygons that are each defined by a set of vertices. Any of the polygons that abut each other are grouped together. Any grouped polygons are healed so as to eliminate interior edges of each set of grouped polygons to obtain a polygon corresponding to a covering region of such set of grouped polygons. Geometric constraints that specify requirements for detecting a plurality of feature classes are provided and used for detecting a plurality of feature classes in the polygons of the design database. The detected features classes are used to detect defects in the mask.

    Loosely-Coupled Inspection and Metrology System for High-Volume Production Process Monitoring

    公开(公告)号:US20200184372A1

    公开(公告)日:2020-06-11

    申请号:US16287523

    申请日:2019-02-27

    Abstract: A metrology system is disclosed. In one embodiment, the metrology system includes a controller communicatively coupled to a reference metrology tool and an optical metrology tool, the controller including one or more processors configured to: generate a geometric model for determining a profile of a test HAR structure from metrology data from a reference metrology tool; generate a material model for determining one or more material parameters of a test HAR structure from metrology data from the optical metrology tool; form a composite model from the geometric model and the material model; measure at least one additional test HAR structure with the optical metrology tool; and determine a profile of the at least one additional test HAR structure based on the composite model and metrology data from the optical metrology tool associated with the at least one HAR test structure.

    POLYGON-BASED GEOMETRY CLASSIFICATION FOR SEMICONDUCTOR MASK INSPECTION
    6.
    发明申请
    POLYGON-BASED GEOMETRY CLASSIFICATION FOR SEMICONDUCTOR MASK INSPECTION 审中-公开
    用于SEMICONDUCTOR MASK检查的基于聚合物的几何分类

    公开(公告)号:US20170046471A1

    公开(公告)日:2017-02-16

    申请号:US15230836

    申请日:2016-08-08

    CPC classification number: G06T7/0006 G06T2207/30148

    Abstract: Disclosed are methods and apparatus for providing feature classification for inspection of a photolithographic mask. A design database for fabrication of a mask includes polygons that are each defined by a set of vertices. Any of the polygons that abut each other are grouped together. Any grouped polygons are healed so as to eliminate interior edges of each set of grouped polygons to obtain a polygon corresponding to a covering region of such set of grouped polygons. Geometric constraints that specify requirements for detecting a plurality of feature classes are provided and used for detecting a plurality of feature classes in the polygons of the design database. The detected features classes are used to detect defects in the mask.

    Abstract translation: 公开了用于提供用于检查光刻掩模的特征分类的方法和装置。 用于制造掩模的设计数据库包括由一组顶点限定的多边形。 彼此相邻的任何多边形组合在一起。 愈合任何分组的多边形,以消除每组分组多边形的内部边缘,以获得对应于这组分组多边形的覆盖区域的多边形。 提供了用于检测多个要素类的要求的几何约束,并用于检测设计数据库的多边形中的多个要素类。 检测到的特征类用于检测掩模中的缺陷。

    Loosely-coupled inspection and metrology system for high-volume production process monitoring

    公开(公告)号:US11562289B2

    公开(公告)日:2023-01-24

    申请号:US16287523

    申请日:2019-02-27

    Abstract: A metrology system is disclosed. In one embodiment, the metrology system includes a controller communicatively coupled to a reference metrology tool and an optical metrology tool, the controller including one or more processors configured to: generate a geometric model for determining a profile of a test HAR structure from metrology data from a reference metrology tool; generate a material model for determining one or more material parameters of a test HAR structure from metrology data from the optical metrology tool; form a composite model from the geometric model and the material model; measure at least one additional test HAR structure with the optical metrology tool; and determine a profile of the at least one additional test HAR structure based on the composite model and metrology data from the optical metrology tool associated with the at least one HAR test structure.

Patent Agency Ranking