公开(公告)号：US20200004234A1

公开(公告)日：2020-01-02

申请号：US16538689

申请日：2019-08-12

Applicant: Applied Materials, Inc.

Inventor： Jimmy ISKANDAR ,  Jianping ZOU ,  Parris C.M. HAWKINS ,  James MOYNE

IPC: G05B23/02

Abstract: Described herein are methods, apparatuses, and systems for reducing equipment repair time. In one embodiment, a computer implemented method includes collecting, with a system, data including test substrate data or other metrology data and fault detection data for maintenance recovery of at least one manufacturing tool in a manufacturing facility and determining, with the system, a relationship between tool parameter settings for the at least one manufacturing tool and at least some collected data including the test substrate data. The method further includes utilizing zero or more virtual metrology predictive algorithms and at least some collected data to obtain a metrology prediction and applying multivariate run-to-run (R2R) control modeling to obtain a state estimation including a current operating region of the at least one manufacturing tool based on the test substrate data and obtain at least one tool parameter adjustment for at least one target parameter for the at least one manufacturing tool. Applying multivariate run-to-run (R2R) control modeling to obtain tool parameter adjustments for at least one manufacturing tool occurs after maintenance to reduce maintenance recovery time and to reduce requalification time.

公开(公告)号：US20170261971A1

公开(公告)日：2017-09-14

申请号：US15457016

申请日：2017-03-13

Applicant: Applied Materials, Inc.

Inventor： Bradley D. SCHULZE ,  Suketu Arun PARIKH ,  Jimmy ISKANDAR ,  Jigar Bhadriklal PATEL

IPC: G05B23/02

CPC classification number: G05B23/0254 ,  G05B23/0232 ,  G05B23/0283 ,  G05B2219/45031

Abstract: Techniques are provided for classifying runs of a recipe within a manufacturing environment. Embodiments monitor a plurality of runs of a recipe to collect runtime data from a plurality of sensors within a manufacturing environment. Qualitative data describing each semiconductor devices produced by the plurality of runs is determined. Embodiments characterize each run into a respective group, based on an analysis of the qualitative data, and generate a data model based on the collected runtime data. A multivariate analysis of additional runtime data collected during at least one subsequent run of the recipe is performed to classify the at least one subsequent run into a first group. Upon classifying the at least one subsequent run, embodiments output for display an interface depicting a ranking sensor types based on the additional runtime data and the description of relative importance of each sensor type for the first group within the data model.

公开(公告)号：US20170343999A1

公开(公告)日：2017-11-30

申请号：US15610280

申请日：2017-05-31

Applicant: Applied Materials, Inc.

Inventor： Jimmy ISKANDAR ,  Michael D. ARMACOST ,  Heng HAO

IPC: G05B23/02 ,  H01L21/67

CPC classification number: G05B23/0291 ,  G05B23/0243

Abstract: Embodiments provide techniques for compressing sensor data collected within a manufacturing environment. One embodiment monitors a plurality of runs of a recipe for fabricating one or more semiconductor devices within a manufacturing environment to collect runtime data from a plurality of sensors within the manufacturing environment. The collected runtime data is compressed by generating, for each of the plurality of sensors and for each of the plurality of runs, a respective representation of the corresponding runtime data that describes a shape of the corresponding runtime data and a magnitude of the corresponding runtime data. A query specifying one or more runtime data attributes is received and executed against the compressed runtime data to generate query results, by comparing the one or more runtime data attributes to at least one of the generated representations of runtime data.

公开(公告)号：US20170045573A1

公开(公告)日：2017-02-16

申请号：US15231487

申请日：2016-08-08

Applicant: Applied Materials, Inc.

Inventor： Jimmy ISKANDAR ,  Chong JIANG ,  Michael D. ARMACOST ,  Bradley D. SCHULZE

IPC: G01R31/26 ,  G06N7/00 ,  G06F17/50 ,  H01L21/66

CPC classification number: G06F17/50 ,  G01R31/2831 ,  G06F17/5068 ,  G06F2217/10 ,  H01L22/12

Abstract: Embodiments presented herein provide techniques for predicting the topography of a product produced from a manufacturing process. One embodiment includes generating a plurality of prediction models. Each of the plurality of prediction models corresponds to a respective one of a plurality of positional coordinates of a product produced from a manufacturing process. The method also includes receiving a set of user-specified input parameters to apply to the manufacturing control process. The method further includes generating a graphical representation of a topography map for the product for the user-specified of input parameters based on the plurality of prediction models.

Abstract translation: 本文提供的实施例提供了用于预测从制造过程产生的产品的形貌的技术。 一个实施例包括生成多个预测模型。 多个预测模型中的每一个对应于从制造过程产生的产品的多个位置坐标中的相应一个。 该方法还包括接收一组用户指定的输入参数以应用于制造控制过程。 该方法还包括基于多个预测模型生成针对用户指定的输入参数的产品的地形图的图形表示。

公开(公告)号：US20160092618A1

公开(公告)日：2016-03-31

申请号：US14841365

申请日：2015-08-31

Applicant: Applied Materials, Inc.

Inventor： Subrahmanyam Venkata Rama KOMMISETTI ,  Haw Jyue LUO ,  Jimmy ISKANDAR ,  Hsincheng LAI ,  Parris HAWKINS

IPC: G06F17/50 ,  G06F7/556

CPC classification number: G06F17/5009 ,  G05B23/0221 ,  G05B23/024 ,  G05B2219/37537 ,  G06F7/556 ,  G06F2207/556

Abstract: Embodiments disclosed herein include methods for reducing or eliminating the impact of tuning disturbances during prediction of lamp failure. In one embodiment, the method comprises monitoring data of a lamp module for a process chamber using one or more physical sensors disposed at different locations within the lamp module, creating virtual sensors based on monitoring data of the lamp module, and providing a prediction model for the lamp module using the virtual sensors as inputs.

Abstract translation: 本文公开的实施例包括用于在灯故障预测期间减少或消除调谐干扰的影响的方法。 在一个实施例中，该方法包括使用布置在灯模块内的不同位置处的一个或多个物理传感器来监视处理室的灯模块的数据，基于灯模块的监视数据创建虚拟传感器，并且为 灯模块使用虚拟传感器作为输入。

公开(公告)号：US20150331980A1

公开(公告)日：2015-11-19

申请号：US14713943

申请日：2015-05-15

Applicant: Applied Materials, Inc.

Inventor： Jimmy ISKANDAR ,  Bradley D. SCHULZE ,  Parris HAWKINS

IPC: G06F17/50 ,  G06F17/30

Abstract: A method is provided for determining two or more context types having an associated fault to be modeled by the same multivariate model. The method includes selecting a fault and selecting two or more context types associated with the fault. The method further includes accessing data stored for the selected context types. The method further includes generating rankings of process data tags for each selected context type. Each ranking includes process data tags ranked according to relative contributions of each process data tag in the ranking to the fault. The method further includes classifying the context types into one or more classes based on the process data tags included in each ranking. The one or more classes include a first class of the context types. The method further includes deploying a multivariate model operable to monitor processing equipment for the selected fault for the first class of context types.

Abstract translation: 提供了一种用于确定具有由相同多变量模型建模的相关故障的两个或多个上下文类型的方法。 该方法包括选择故障并选择与故障相关联的两个或多个上下文类型。 该方法还包括访问为所选择的上下文类型存储的数据。 该方法还包括为每个所选择的上下文类型生成过程数据标签的排名。 每个排名包括根据每个过程数据标签在与故障排序中的相对贡献进行排序的过程数据标签。 该方法还包括基于每个排名中包括的过程数据标签将上下文类型分类为一个或多个类。 一个或多个类包括上下文类型的第一类。 该方法还包括部署多变量模型，其可操作以监视针对第一类上下文类型的所选择的故障的处理设备。

公开(公告)号：US20150302311A1

公开(公告)日：2015-10-22

申请号：US14254811

申请日：2014-04-16

Applicant: Applied Materials, Inc.

Inventor： Jimmy ISKANDAR ,  Bradley D. SCHULZE ,  Kommisetti SUBRAHMANYAM ,  Haw-Jyue LUO

IPC: G06N5/04

CPC classification number: G06N5/048

Abstract: A method is provided for determining one or more causes for variability in data. The method includes selecting a first range of a multivariate model output data on a user interface and employing a computing system, operatively coupled to the user interface, to determine one or more process data causing a variability of the multivariate model output data in the first range when compared to a second range of the multivariate model output data. At least some of the process data includes data derived from a physical measurement of a process variable.

Abstract translation: 提供了一种用于确定数据变异性的一个或多个原因的方法。 该方法包括在用户接口上选择多变量模型输出数据的第一范围并采用可操作地耦合到用户界面的计算系统来确定导致第一范围内的多变量模型输出数据的可变性的一个或多个过程数据 当与多变量模型输出数据的第二范围相比时。 过程数据中的至少一些包括从过程变量的物理测量导出的数据。