Defect classification with optimized purity
    2.
    发明授权
    Defect classification with optimized purity 有权
    缺陷分类,优化纯度

    公开(公告)号:US08315453B2

    公开(公告)日:2012-11-20

    申请号:US12844724

    申请日:2010-07-27

    IPC分类号: G06K9/00

    摘要: A method for defect analysis includes identifying single-class classifiers for a plurality of defect classes, the plurality of defect classes characterized by respective ranges of inspection parameter values. Each single-class classifier is configured for a respective class to identify defects belonging to the respective class based on the inspection parameter values, while identifying the defects not in the respective class as unknown defects. A multi-class classifier is identified that is configured to assign each defect to one of the plurality of the defect classes based on the inspection parameter values. Inspection data is received, and both the single-class and multi-class classifiers are applied to the inspection data to assign the defect to one of the defect classes.

    摘要翻译: 用于缺陷分析的方法包括识别多个缺陷类别的单类分类器,所述多个缺陷类别由检查参数值的相应范围表征。 每个单类分类器被配置用于相应的类,以基于检查参数值来识别属于相应类的缺陷,同时将不在相应类中的缺陷识别为未知缺陷。 识别被配置为基于检查参数值将每个缺陷分配给多个缺陷类别中的一个的多类分类器。 接收到检查数据,并将单类和多类分类器应用于检查数据,以将缺陷分配给缺陷类之一。

    CLASSIFIER READINESS AND MAINTENANCE IN AUTOMATIC DEFECT CLASSIFICATION
    3.
    发明申请
    CLASSIFIER READINESS AND MAINTENANCE IN AUTOMATIC DEFECT CLASSIFICATION 有权
    分类器在自动缺陷分类中的阅读和维护

    公开(公告)号:US20130279796A1

    公开(公告)日:2013-10-24

    申请号:US13452771

    申请日:2012-04-20

    IPC分类号: G06K9/62 G06K9/00

    摘要: A method for classification includes receiving inspection data associated with a plurality of defects found in one or more samples and receiving one or more benchmark classification comprising a class for each of the plurality of defects. a readiness criterion for one or more of the classes is evaluated based on the one or more benchmark classification results, wherein the readiness criterion comprises for each class, a suitability of the inspection data for training an automatic defect classifier for the class. A portion of the inspection data is selected corresponding to one or more defects associated with one or more classes that satisfy the readiness criterion. One or more automatic classifiers are trained for the one or more classes that satisfy the readiness criterion using the selected portion of the inspection data.

    摘要翻译: 一种用于分类的方法包括接收与一个或多个样本中发现的多个缺陷相关联的检查数据,并且接收一个或多个基准分类,其包括针对所述多个缺陷中的每一个的类别。 基于一个或多个基准分类结果来评估一个或多个类的准备标准,其中准备准则包括对于每个类别,用于训练用于该类的自动缺陷分类器的检查数据的适合性。 对应于与满足准备标准的一个或多个类别相关联的一个或多个缺陷来选择检查数据的一部分。 使用检查数据的所选部分,针对满足准备标准的一个或多个类训练一个或多个自动分类器。

    OPTIMIZATION OF UNKNOWN DEFECT REJECTION FOR AUTOMATIC DEFECT CLASSIFICATION
    4.
    发明申请
    OPTIMIZATION OF UNKNOWN DEFECT REJECTION FOR AUTOMATIC DEFECT CLASSIFICATION 有权
    自动缺陷分类的未知缺陷抑制优化

    公开(公告)号:US20130279795A1

    公开(公告)日:2013-10-24

    申请号:US13451500

    申请日:2012-04-19

    IPC分类号: G06K9/62

    摘要: A method for defect classification includes storing, in a computer system, a definition of a region in a feature space. The definition is associated with a class of defects and comprises a kernel function comprising a parameter. The parameter determines a shape of the region. A confidence threshold for automatic classification of at least one defect associated with the class is received. A value of the parameter associated with the confidence threshold is selected. Inspection data for a plurality of defects detected in one or more samples under inspection is received. The plurality of defects for the class are automatically classified using the kernel function and the selected value of the parameter.

    摘要翻译: 一种用于缺陷分类的方法包括在计算机系统中存储特征空间中的区域的定义。 该定义与一类缺陷相关联,并且包括包含参数的核心函数。 该参数确定区域的形状。 接收到与该类相关联的至少一个缺陷的自动分类的置信阈值。 选择与置信阈值相关联的参数的值。 接收在检查中的一个或多个样本中检测到的多个缺陷的检查数据。 该类的多个缺陷使用内核函数和参数的选定值进行自动分类。

    DEFECT CLASSIFICATION WITH OPTIMIZED PURITY
    5.
    发明申请
    DEFECT CLASSIFICATION WITH OPTIMIZED PURITY 有权
    优化分类与优化

    公开(公告)号:US20120027285A1

    公开(公告)日:2012-02-02

    申请号:US12844724

    申请日:2010-07-27

    IPC分类号: G06K9/00

    摘要: A method for defect analysis includes identifying single-class classifiers for a plurality of defect classes, the plurality of defect classes characterized by respective ranges of inspection parameter values. Each single-class classifier is configured for a respective class to identify defects belonging to the respective class based on the inspection parameter values, while identifying the defects not in the respective class as unknown defects. A multi-class classifier is identified that is configured to assign each defect to one of the plurality of the defect classes based on the inspection parameter values. Inspection data is received, and both the single-class and multi-class classifiers are applied to the inspection data to assign the defect to one of the defect classes.

    摘要翻译: 用于缺陷分析的方法包括识别多个缺陷类别的单类分类器,所述多个缺陷类别由检查参数值的相应范围表征。 每个单类分类器被配置用于相应的类,以基于检查参数值来识别属于相应类的缺陷,同时将不在相应类中的缺陷识别为未知缺陷。 识别被配置为基于检查参数值将每个缺陷分配给多个缺陷类别中的一个的多类分类器。 接收到检查数据,并将单类和多类分类器应用于检查数据,以将缺陷分配给缺陷类之一。

    Method and apparatus for controlling a stepper motor with a programmable
parabolic velocity profile
    6.
    发明授权
    Method and apparatus for controlling a stepper motor with a programmable parabolic velocity profile 失效
    用可控抛物线速度分布控制步进电机的方法和装置

    公开(公告)号:US4714867A

    公开(公告)日:1987-12-22

    申请号:US913537

    申请日:1986-09-30

    摘要: A stepper motor is accelerated and decelerated with a parabolic velocity profile to efficiently utilize the available torque of the motor. The times between pulses to obtain a parabolic velocity profile are determined by a microprocessor-based stepper motor controller from desired values of start/stop velocity, maximum velocity and time to reach maximum velocity. The required times are stored in a random access memory and are used to supply to the motor a pulse train which follows the parabolic velocity profile during acceleration and deceleration. The controller is easily programmable to accommodate different motor characteristics, different applications and different operating parameters.

    摘要翻译: 步进电机以抛物线速度曲线加速和减速,以有效利用电机的可用转矩。 获得抛物线速度曲线的脉冲之间的时间由基于微处理器的步进电动机控制器根据期望的开始/停止速度值,最大速度和时间达到最大速度来确定。 所需的时间存储在随机存取存储器中,并且用于在加速和减速期间向马达提供跟随抛物线速度分布的脉冲串。 控制器易于编程,适应不同的电机特性,不同的应用和不同的工作参数。