公开(公告)号：US20160041548A1

公开(公告)日：2016-02-11

申请号：US14485280

申请日：2014-09-12

Applicant: United Microelectronics Corp.

Inventor： Feng-Chi Chung ,  Ching-Hsing Hsieh ,  Yi-Chun Lin ,  Chien-Chuan Yu

IPC: G05B19/401

CPC classification number: G05B23/0221 ,  G03F7/70608 ,  G03F7/70616

Abstract: A virtual metrology system and a method therefor are provided herein. In the system, a set of process data is gathered and clustered according to a plurality of predetermined patterns. The clustered set of process data is calculated according to the corresponding pattern, so as to obtain a comparison result. If the obtained result meets a desired output, a corresponding step is performed based on the result. In one case, the corresponding step is a normal sampling step if the clustered set of process data meets the corresponding pattern. If the clustered set of process data does not meet the corresponding pattern, an alarm is generated thereby, and the corresponding equipment may be shut down. In another case, the corresponding step is a maintenance, repair, and overhaul step if the clustered set of process data meets the corresponding pattern.

Abstract translation: 本文提供了虚拟计量系统及其方法。 在该系统中，根据多个预定模式收集和聚类一组过程数据。 根据相应的模式计算聚类过程数据集，以获得比较结果。 如果获得的结果满足期望的输出，则基于该结果执行相应的步骤。 在一种情况下，如果聚集的过程数据集合满足相应模式，相应步骤是正常采样步骤。 如果集群过程数据不符合相应模式，则会产生报警，并且相应的设备可能会关闭。 在另一种情况下，相应的步骤是维护，修复和大修步骤，如果集群过程数据符合相应的模式。

公开(公告)号：US20160031056A1

公开(公告)日：2016-02-04

申请号：US14451406

申请日：2014-08-04

Applicant: UNITED MICROELECTRONICS CORP.

Inventor： Feng-Chi Chung ,  Ching-Hsing Hsieh ,  Chen-Hui Huang ,  Hsin-Kun Chu

IPC: B23Q15/28

CPC classification number: G05B19/41875 ,  G05B2219/32182 ,  G05B2219/45031 ,  Y02P90/22 ,  Y02P90/86

Abstract: A method of a fault detection and classification (FDC) may be used to determine outlier tools from a plurality of tools. The method includes generating a plurality of parameter charts, generating a plurality of group charts according to the plurality of parameter charts, generating a score table according to the plurality of group charts, determining outlier tools according to the score table, and performing tool correction on the outlier tools.

Abstract translation: 可以使用故障检测和分类（FDC）的方法来从多个工具确定异常工具。 该方法包括生成多个参数图，根据多个参数图生成多个组图，根据多个组图生成分数表，根据分数表确定异常值工具，并对 异常工具。

公开(公告)号：US10606253B2

公开(公告)日：2020-03-31

申请号：US15427279

申请日：2017-02-08

Applicant: UNITED MICROELECTRONICS CORP.

Inventor： Lian-Hua Shih ,  Chia-Chi Chang ,  Li-Ting Lin ,  Ching-Hsing Hsieh ,  Feng-Chi Chung ,  Meng-Chih Chang ,  Ming-Tung Wang ,  Chiu-Ping Chang ,  Yung-Yu Yang

IPC: G05B23/02

Abstract: A method of monitoring a processing system for processing a substrate is provided. The method includes the following steps: acquiring data from the processing system for a plurality of parameters, the data including a plurality of data values; grouping the parameters into a plurality of sub-groups, each of the sub-groups including a plurality of correlated parameters; constructing a principle components analysis (PCA) model from the data values for the correlated parameters in a first one of the sub-groups, including normalizing the data values in the first one of the sub-groups with a first weighting factor and a second weighting factor, wherein the first weighting factor is different from the second weighting factor; and determining a statistical quantity using the PCA model.

公开(公告)号：US20160274570A1

公开(公告)日：2016-09-22

申请号：US14660961

申请日：2015-03-18

Applicant: UNITED MICROELECTRONICS CORP.

Inventor： Lian-Hua Shih ,  Ching-Hsing Hsieh ,  Feng-Chi Chung ,  Chia-Chi Chang ,  Yu-Cheng Lin ,  Sian-Jhu Tsai ,  Meng-Chih Chang ,  Yi-Hui Tseng

IPC: G05B19/4097 ,  G05B15/02

CPC classification number: G05B19/41875 ,  G05B2219/32194 ,  G05B2219/37224 ,  Y02P90/22

Abstract: A method of virtual metrology is disclosed. Process data and measurement values corresponding to a workpiece are collected. The process data and the measurement values are used to establish a conjecture model. A theoretical model corresponding to the workpiece and the conjecture model is used to establish another conjecture model. The another conjecture model is used to establish a virtual metrology value. The virtual metrology value is used to predict properties of a subsequently manufactured workpiece.

Abstract translation: 公开了一种虚拟测量方法。 收集与工件对应的工艺数据和测量值。 过程数据和测量值用于建立猜想模型。 使用对应于工件和推测模型的理论模型来建立另一个推测模型。 另一个猜想模型用于建立虚拟计量学值。 虚拟计量值用于预测随后制造的工件的性能。

公开(公告)号：US10935969B2

公开(公告)日：2021-03-02

申请号：US16285067

申请日：2019-02-25

Applicant: United Microelectronics Corp.

Inventor： Feng-Chi Chung ,  Ching-Hsing Hsieh ,  Yi-Chun Lin ,  Chien-Chuan Yu

IPC: G05B23/02 ,  G03F7/20

Abstract: A virtual metrology system at least includes a process apparatus including a set of process data, the process apparatus producing a workpiece according to the set of process data. A virtual metrology server is configured to gather the set of process data, cluster the set of process data to obtain data clusters, and compare the data clusters with patterns. If the data clusters meet the patterns corresponding to the data clusters, performing a corresponding maintenance, repair, and overhaul step on the process apparatus.

公开(公告)号：US20190187674A1

公开(公告)日：2019-06-20

申请号：US16285067

申请日：2019-02-25

Applicant: United Microelectronics Corp.

Inventor： Feng-Chi Chung ,  Ching-Hsing Hsieh ,  Yi-Chun Lin ,  Chien-Chuan Yu

IPC: G05B23/02

CPC classification number: G05B23/0221 ,  G03F7/70608 ,  G03F7/70616

Abstract: A virtual metrology system at least includes a process apparatus including a set of process data, the process apparatus producing a workpiece according to the set of process data. A virtual metrology server is configured to gather the set of process data, cluster the set of process data to obtain data clusters, and compare the data clusters with patterns. If the data clusters meet the patterns corresponding to the data clusters, performing a corresponding maintenance, repair, and overhaul step on the process apparatus.

公开(公告)号：US10261504B2

公开(公告)日：2019-04-16

申请号：US14485280

申请日：2014-09-12

Applicant: United Microelectronics Corp.

Inventor： Feng-Chi Chung ,  Ching-Hsing Hsieh ,  Yi-Chun Lin ,  Chien-Chuan Yu

IPC: G05B23/02 ,  G03F7/20

Abstract: A virtual metrology system and a method therefor are provided herein. In the system, a set of process data is gathered and clustered according to a plurality of predetermined patterns. The clustered set of process data is calculated according to the corresponding pattern, so as to obtain a comparison result. If the obtained result meets a desired output, a corresponding step is performed based on the result. In one case, the corresponding step is a normal sampling step if the clustered set of process data meets the corresponding pattern. If the clustered set of process data does not meet the corresponding pattern, an alarm is generated thereby, and the corresponding equipment may be shut down. In another case, the corresponding step is a maintenance, repair, and overhaul step if the clustered set of process data meets the corresponding pattern.

公开(公告)号：US20180224817A1

公开(公告)日：2018-08-09

申请号：US15427279

申请日：2017-02-08

Applicant: UNITED MICROELECTRONICS CORP.

Inventor： Lian-Hua Shih ,  Chia-Chi Chang ,  Li-Ting Lin ,  Ching-Hsing Hsieh ,  Feng-Chi Chung ,  Meng-Chih Chang ,  Ming-Tung Wang ,  Chiu-Ping Chang ,  Yung-Yu Yang

IPC: G05B19/048 ,  G06F17/30 ,  G05B17/02

CPC classification number: G05B23/024

Abstract: A method of monitoring a processing system for processing a substrate is provided. The method includes the following steps: acquiring data from the processing system for a plurality of parameters, the data including a plurality of data values; grouping the parameters into a plurality of sub-groups, each of the sub-groups including a plurality of correlated parameters; constructing a principle components analysis (PCA) model from the data values for the correlated parameters in a first one of the sub-groups, including normalizing the data values in the first one of the sub-groups with a first weighting factor and a second weighting factor, wherein the first weighting factor is different from the second weighting factor; and determining a statistical quantity using the PCA model.