Inspection of reticles using machine learning

    公开(公告)号:US11257207B2

    公开(公告)日:2022-02-22

    申请号:US16201788

    申请日:2018-11-27

    Abstract: Disclosed are methods and apparatus for inspecting a photolithographic reticle. A near field reticle image is generated via a deep learning process based on a reticle database image produced from a design database, and a far field reticle image is simulated at an image plane of an inspection system via a physics-based process based on the near field reticle image. The deep learning process includes training a deep learning model based on minimizing differences between the far field reticle images and a plurality of corresponding training reticle images acquired by imaging a training reticle fabricated from the design database, and such training reticle images are selected for pattern variety and are defect-free. A test area of a test reticle, which is fabricated from the design database, is inspected for defects via a die-to-database process that includes comparing a plurality of references images from a reference far field reticle image to a plurality of test images acquired by the inspection system from the test reticle. The reference far field reticle image is simulated based on a reference near field reticle image that is generated by the trained deep learning model.

    Inspection system with non-circular pupil

    公开(公告)号:US11112691B2

    公开(公告)日:2021-09-07

    申请号:US16258118

    申请日:2019-01-25

    Abstract: An inspection system includes an illumination source configured to generate extreme ultraviolet (EUV) light, illumination optics to direct the EUV light to a sample within a range of off-axis incidence angles corresponding to an illumination pupil distribution, collection optics to collect light from the sample in response to the incident EUV light within a range of collection angles corresponding to an imaging pupil distribution, and a detector configured to receive at least a portion of the light collected by the collection optics. Further, a center of the illumination pupil distribution corresponds to an off-axis incidence angle along a first direction on the sample, and at least one of the illumination pupil distribution or the imaging pupil distribution is non-circular with a size along the first direction shorter than along a second direction perpendicular to the first direction.

    Qualifying patterns for microlithography

    公开(公告)号:US09612541B2

    公开(公告)日:2017-04-04

    申请号:US14461638

    申请日:2014-08-18

    Abstract: Disclosed are methods and apparatus for qualifying a photolithographic reticle. A reticle inspection tool is used to acquire at least two images at different imaging configurations from each pattern area of the reticle. A reticle pattern is reconstructed based on each at least two images from each pattern area of the reticle. For each reconstructed reticle pattern, a lithographic process with two or more different process conditions is modeled on such reconstructed reticle pattern to generate two or more corresponding modeled test wafer patterns. Each two or more modelled test wafer patterns is analyzed to identify hot spot patterns of the reticle patterns that are susceptible to the different process conditions altering wafer patterns formed with such hot spot patterns.

    Apparatus and methods for predicting wafer-level defect printability
    15.
    发明授权
    Apparatus and methods for predicting wafer-level defect printability 有权
    用于预测晶圆级缺陷可印刷性的装置和方法

    公开(公告)号:US09547892B2

    公开(公告)日:2017-01-17

    申请号:US14822571

    申请日:2015-08-10

    Abstract: Disclosed are methods and apparatus for qualifying a photolithographic reticle. A reticle inspection tool is used to acquire images at different imaging configurations from each of the pattern areas of a calibration reticle. A reticle near field is recovered for each of the pattern areas of the calibration reticle based on the acquired images from each pattern area of the calibration reticle. Using the recovered reticle near field for the calibration reticle, a lithography model for simulating wafer images is generated based on the reticle near field. Images are then acquired at different imaging configurations from each of the pattern areas of a test reticle. A reticle near field for the test reticle is then recovered based on the acquired images from the test reticle. The generated model is applied to the reticle near field for the test reticle to simulate a plurality of test wafer images, and the simulated test wafer images are analyzed to determine whether the test reticle will likely result in an unstable or defective wafer.

    Abstract translation: 公开了用于限定光刻掩模版的方法和装置。 使用掩模版检查工具从校准掩模版的每个图案区域获取不同成像配置的图像。 基于从校准掩模版的每个图案区域获取的图像,对校准掩模版的每个图案区域恢复光栅近场。 使用恢复的光栅近场用于校准掩模版,基于掩模版近场产生用于模拟晶片图像的光刻模型。 然后以与测试掩模版的每个图案区域不同的成像配置获取图像。 然后根据获得的来自测试掩模版的图像来恢复用于测试掩模版的近距离掩模版。 将生成的模型应用于测试光罩的光栅近场,以模拟多个测试晶片图像,并分析模拟的测试晶片图像,以确定测试光罩是否可能导致晶片不稳定或缺陷。

    Block-to-Block Reticle Inspection
    16.
    发明申请
    Block-to-Block Reticle Inspection 有权
    块到块标线检查

    公开(公告)号:US20150078650A1

    公开(公告)日:2015-03-19

    申请号:US14466688

    申请日:2014-08-22

    Abstract: Block-to-block reticle inspection includes acquiring a swath image of a portion of a reticle with a reticle inspection sub-system, identifying a first occurrence of a block in the swatch image and at least a second occurrence of the block in the swath image substantially similar to the first occurrence of the block and determining at least one of a location, one or more geometrical characteristics of the block and a spatial offset between the first occurrence of the block and the at least a second occurrence of the block.

    Abstract translation: 块对块掩模版检查包括用掩模版检查子系统获取掩模版的一部分的条带图像,识别样本图像中的块的第一次出现以及条纹图像中的块的至少第二次出现 基本上类似于块的第一次出现并且确定块的位置,一个或多个几何特征和块的第一次出现与块的至少第二次出现之间的空间偏移中的至少一个。

    QUALIFYING PATTERNS FOR MICROLITHOGRAPHY
    17.
    发明申请
    QUALIFYING PATTERNS FOR MICROLITHOGRAPHY 有权
    用于微结构的质量模式

    公开(公告)号:US20150054940A1

    公开(公告)日:2015-02-26

    申请号:US14461638

    申请日:2014-08-18

    Abstract: Disclosed are methods and apparatus for qualifying a photolithographic reticle. A reticle inspection tool is used to acquire at least two images at different imaging configurations from each pattern area of the reticle. A reticle pattern is reconstructed based on each at least two images from each pattern area of the reticle. For each reconstructed reticle pattern, a lithographic process with two or more different process conditions is modeled on such reconstructed reticle pattern to generate two or more corresponding modeled test wafer patterns. Each two or more modelled test wafer patterns is analyzed to identify hot spot patterns of the reticle patterns that are susceptible to the different process conditions altering wafer patterns formed with such hot spot patterns.

    Abstract translation: 公开了用于限定光刻掩模版的方法和装置。 掩模版检查工具用于从掩模版的每个图案区域获取不同成像配置的至少两个图像。 基于每个至少两个来自掩模版的图案区域的图像来重建掩模版图案。 对于每个重建的掩模版图案,具有两个或多个不同工艺条件的光刻工艺在这种重建的掩模版图案上被建模以产生两个或更多个相应的建模测试晶片图案。 分析每两个或更多个建模的测试晶片图案,以识别对不同工艺条件敏感的改变由这种热点图案形成的晶片图案的掩模版图案的热点图案。

    Inspection of reticles using machine learning

    公开(公告)号:US12094101B2

    公开(公告)日:2024-09-17

    申请号:US17456415

    申请日:2021-11-24

    Abstract: Disclosed are methods and apparatus for inspecting a photolithographic reticle. A plurality of reference far field images are simulated by inputting a plurality of reference near field images into a physics-based model, and the plurality of reference near field images are generated by a trained deep learning model from a test portion of the design database that was used to fabricate a test area of a test reticle. The test area of a test reticle, which was fabricated from the design database, is inspected for defects via a die-to-database process that includes comparing the plurality of reference far field reticle images simulated by the physic-based model to a plurality of test images acquired by the inspection system from the test area of the test reticle.

    Inspection System with Non-Circular Pupil
    19.
    发明申请

    公开(公告)号:US20200225574A1

    公开(公告)日:2020-07-16

    申请号:US16258118

    申请日:2019-01-25

    Abstract: An inspection system includes an illumination source configured to generate extreme ultraviolet (EUV) light, illumination optics to direct the EUV light to a sample within a range of off-axis incidence angles corresponding to an illumination pupil distribution, collection optics to collect light from the sample in response to the incident EUV light within a range of collection angles corresponding to an imaging pupil distribution, and a detector configured to receive at least a portion of the light collected by the collection optics. Further, a center of the illumination pupil distribution corresponds to an off-axis incidence angle along a first direction on the sample, and at least one of the illumination pupil distribution or the imaging pupil distribution is non-circular with a size along the first direction shorter than along a second direction perpendicular to the first direction.

    Critical dimension uniformity monitoring for extreme ultra-violet reticles

    公开(公告)号:US10288415B2

    公开(公告)日:2019-05-14

    申请号:US15826529

    申请日:2017-11-29

    Abstract: Disclosed are methods and apparatus for facilitating an inspection of a sample using an inspection tool. An inspection tool is used to obtain an image or signal from an EUV reticle that specifies an intensity variation across the EUV reticle, and this intensity variation is converted to a CD variation that removes a flare correction CD variation so as to generate a critical dimension uniformity (CDU) map without the flare correction CD variation. This removed flare correction CD variation originates from design data for fabricating the EUV reticle, and such flare correction CD variation is generally designed to compensate for flare differences that are present across a field of view (FOV) of a photolithography tool during a photolithography process. The CDU map is stored in one or more memory devices and/or displayed on a display device, for example, of the inspection tool or a photolithography system.

Patent Agency Ranking