公开(公告)号：US11984334B2

公开(公告)日：2024-05-14

申请号：US17229293

申请日：2021-04-13

申请人： Accenture Global Solutions Limited

发明人： Makoto Murai ,  Shin Moriga ,  Atsushi Suyama ,  Motoaki Hayashi ,  Takuya Kudo

IPC分类号： H01L21/67 ,  G05B19/418 ,  G06N20/00

CPC分类号： H01L21/67276 ,  G05B19/41875 ,  G05B2219/32179 ,  G06N20/00

摘要： The present disclosure describes a computer-implemented method for detecting anomalies during lot production, wherein the products within a production lot are processed according to a sequence of steps that include manufacturing steps and one or more quality control steps interspersed among the manufacturing steps, the method comprising: obtaining process quality inspection data from each of the one or more quality control steps for a first production lot; obtaining product characteristics data for the products in the first production lot after the final step in the sequence; training a Gaussian process regression model using the process quality inspection data and the product characteristics data from the first production lot; generating a predictive distribution of the product characteristics data using the Gaussian process regression model that uses a bathtub kernel function; obtaining process quality inspection data from each of the quality control steps for a second production lot; identifying anomalies in the second production lot using the predictive distribution of the product characteristics data and the process quality inspection data from the second production lot; if no anomalies are detected in the second production lot, updating the Gaussian process regression model using the process quality inspection data from the second production lot; setting target values for one or more values in the process quality inspection data based on the predictive distribution of the product characteristic; and adjusting settings of one or more manufacturing steps based on the target values.

公开(公告)号：US20230185289A1

公开(公告)日：2023-06-15

申请号：US17924883

申请日：2020-06-05

申请人： Mitsubishi Electric Corporation

发明人： Kotaro SANAI ,  Emi YONEDA ,  Masayo NAKAGAWA

IPC分类号： G05B19/418

CPC分类号： G05B19/41875 ,  G05B2219/32179

摘要： An abnormality symptom analyzing device comprises: a data request receiver to perform request and reception of data, required for analyzing an abnormality symptom(s), including measurement information obtained from a sensor(s) of a facility, an abnormality symptom(s) detected from the measurement information and inspection information of the facility; a data storage device to store the data acquired by the data request receiver; a coordination circuitry to perform the registration of data to display a screen display component(s) on a display device and the correspondence of data coordinated between screen display components to a screen display component(s) coordinated, and to store information modified according to input contents from an input device, whereby modification contents are coordinated to the screen display components; and a component graphics-drawing management circuitry to acquire data through the coordination circuitry, and to display details information of the facility and propagation information of an abnormality symptom(s) in signals.

公开(公告)号：US11650579B2

公开(公告)日：2023-05-16

申请号：US16809713

申请日：2020-03-05

申请人： FUJITSU LIMITED

发明人： Kazunori Maruyama ,  Takeshi Soeda

IPC分类号： G05B23/02

CPC分类号： G05B23/0245 ,  G05B2219/32179 ,  G05B2223/02

摘要： An information processing device includes: a memory; and a processor coupled to the memory and configured to: learn a classification rule that classifies an abnormal degree of a production facility from a text feature amount based on the text feature amount obtained from a number of texts included in a plurality of pieces of log data obtained in a predetermined process of the production facility and production history information of the production facility; extract a text feature amount of log data to be monitored obtained in the predetermined process of the production facility; and determine an abnormal degree of the production facility when the log data to be monitored is obtained based on the text feature amount and the classification rule.

公开(公告)号：US09836045B2

公开(公告)日：2017-12-05

申请号：US14478204

申请日：2014-09-05

申请人： Kabushiki Kaisha Toshiba

发明人： Takashi Magara

IPC分类号： G05B19/418

CPC分类号： G05B19/41875 ,  G05B2219/32177 ,  G05B2219/32179 ,  Y02P90/14 ,  Y02P90/22

摘要： According to one embodiment, a manufacturing apparatus control system includes a defect rate detector, a significant difference tester and a defect determining unit. The defect rate detector extracts a first apparatus passage history having a first defect rate. The defect rate detector detects a third defect rate by excluding a second apparatus passage history having a second defect rate from the first apparatus passage history. The significant difference tester calculates a significant difference test value. The defect determining unit extracts a third apparatus passage history based on the third defect rate and the significant difference test value.

公开(公告)号：US20130110263A1

公开(公告)日：2013-05-02

申请号：US13664347

申请日：2012-10-30

申请人： Applied Materials, Inc.

发明人： Brad Schulze ,  Joseph Dox

IPC分类号： G05B9/02

CPC分类号： G05B19/41875 ,  G05B23/0272 ,  G05B2219/32179 ,  G05B2219/32201 ,  G05B2219/32222 ,  G05B2219/45031 ,  Y02P90/22

摘要： A method and system for linking sensor data to metrology data and metrology data to sensor data is described herein. In one embodiment, a user selection of metrology data for a product is received, related process tool fault detection summary for the selected metrology data for the product is presented, a user selection of a process tool from the process tool fault detection summary is received, and related fault detection details for the selected process tool are presented.

摘要翻译： 本文描述了用于将传感器数据与度量数据和度量数据链接到传感器数据的方法和系统。 在一个实施例中，接收用户对产品的度量数据的选择，呈现用于产品的所选度量数据的相关过程工具故障检测摘要，接收来自处理工具故障检测摘要的用户对过程工具的选择， 并提供了所选过程工具的相关故障检测细节。

公开(公告)号：US20110178627A1

公开(公告)日：2011-07-21

申请号：US12688530

申请日：2010-01-15

申请人： David Wechter ,  John C. Boetcher ,  Matthew P. Garrison ,  Daryl J. Muma ,  James A. Carter

发明人： David Wechter ,  John C. Boetcher ,  Matthew P. Garrison ,  Daryl J. Muma ,  James A. Carter

IPC分类号： G06F17/00 ,  G06F3/048

CPC分类号： G05B19/41875 ,  G05B2219/32177 ,  G05B2219/32179 ,  G05B2219/32214 ,  Y02P90/22

摘要： A menu-driven manufacturing technique includes determining a product and product configuration, along with process steps to be carried out in manufacturing workstations. Display screens corresponding to the particular manufacturing process steps are accessed and displayed on monitors at the workstations to lead operators through the processes. Control circuitry may verify that the correct components and tools are utilized as called for by the various process steps. Powered tools and test setups may be integrated with the system to enable improved quality control.

摘要翻译： 菜单驱动的制造技术包括确定产品和产品配置，以及在制造工作站中执行的工艺步骤。 对应于特定制造工艺步骤的显示屏幕被访问并显示在工作站上的监视器上，以引导操作者进行这些处理。 控制电路可以根据各种工艺步骤的要求来验证是否使用正确的组件和工具。 电动工具和测试设置可以与系统集成，以实现改进的质量控制。

公开(公告)号：US20090099991A1

公开(公告)日：2009-04-16

申请号：US12255698

申请日：2008-10-22

申请人： Hieu A. LAM ,  Hongyu Yue ,  John Shriner

发明人： Hieu A. LAM ,  Hongyu Yue ,  John Shriner

IPC分类号： G06N5/02

CPC分类号： H01L22/20 ,  G05B19/41875 ,  G05B23/0254 ,  G05B2219/31357 ,  G05B2219/32179 ,  G05B2219/32194 ,  G05B2219/45028 ,  G05B2219/45031 ,  H01J37/32935 ,  Y02P90/14 ,  Y02P90/22

摘要： A method for constructing a process performance prediction model for a material processing system, the method including the steps of: recording tool data for a plurality of observations during a process in a process tool, the tool data comprises a plurality of tool data parameters; recording process performance data for the plurality of observations during the process in the process tool, the process performance data comprises one or more process performance parameters; performing a partial least squares analysis using the tool data and the process performance data; and computing correlation data from the partial least squares analysis.

摘要翻译： 一种用于构建材料处理系统的过程性能预测模型的方法，所述方法包括以下步骤：在处理工具中的处理期间记录多个观察值的工具数据，所述工具数据包括多个工具数据参数; 在所述过程工具中的过程期间记录所述多个观察值的过程性能数据，所述过程执行数据包括一个或多个过程性能参数; 使用工具数据和过程执行数据执行偏最小二乘法分析; 并从偏最小二乘法分析计算相关数据。

公开(公告)号：US07100093B2

公开(公告)日：2006-08-29

申请号：US10209382

申请日：2002-07-29

申请人： Jari Kallela ,  Gerhard Vollmar ,  Szanislo Szöke

发明人： Jari Kallela ,  Gerhard Vollmar ,  Szanislo Szöke

IPC分类号： G06F11/00

CPC分类号： G06Q10/06 ,  G05B19/41875 ,  G05B23/0248 ,  G05B23/0278 ,  G05B2219/32179 ,  G05B2219/32196 ,  G05B2219/32214 ,  G05B2219/32221 ,  Y02P90/14 ,  Y02P90/18 ,  Y02P90/22

摘要： A method is described for the automated determination of fault events by evaluation of field data of a production installation within a system for determining the effectiveness (overall equipment effectiveness (OEE)) of the production installation and for the analysis of causes of faults. The determination of the fault events takes place using a data processing device and programs stored in it for carrying out the functions of a fault event detector and an OEE script configurer. The OEE script configurer accesses a prescribed productivity model specific to a production installation type, generates an OEE script with likewise prescribed configuration data taken into account and stores it in an OEE script memory. The fault event detector accesses the OEE script, calls up field data from a data server, derives fault events from the field data according to processing instructions of the OEE script, and stores them in a fault database.

公开(公告)号：US20050278053A1

公开(公告)日：2005-12-15

申请号：US10853790

申请日：2004-05-26

申请人： Tong-Lung Chia

发明人： Tong-Lung Chia

IPC分类号： G05B23/02 ,  G06F19/00

CPC分类号： G05B23/0227 ,  G05B2219/32179 ,  G05B2219/32207 ,  G05B2219/32221 ,  G05B2219/32385 ,  G05B2219/45031 ,  Y02P90/14 ,  Y02P90/22 ,  Y02P90/26

摘要： The present disclosure provides a semiconductor manufacturing fault detection and management system and method for monitoring at least one manufacturing entity to detect state changes.

摘要翻译： 本公开提供了一种用于监视至少一个制造实体以检测状态变化的半导体制造故障检测和管理系统和方法。

公开(公告)号：US20020173935A1

公开(公告)日：2002-11-21

申请号：US10142904

申请日：2002-05-13

申请人： SOFTROX CO., LTD.

发明人： Kenji Miura

IPC分类号： G06F011/30 ,  G06F015/00 ,  G21C017/00

CPC分类号： G05B19/41875 ,  G05B2219/32179 ,  G05B2219/37223 ,  Y02P90/14 ,  Y02P90/22 ,  Y02P90/28

摘要： Disclosed is a monitoring device for a machine tool, which monitors operations in work machining to increase the precision level of the yield of the work. To monitor a load current supplied to a machining motor in 1-cycle units which run from the start of the machining to the end of the machining, sampling points are taken at shorter intervals along the time axis of the machining in areas where the machining is complex, and in areas where the machining is simple sampling points are taken at longer intervals along the time axis of the machining; and at each sampling point the sampling data are stored and undergo numerical processing. Then, the actually measured value of the load current is compared to determine whether or not the actually measured value is within a range of an upper and a lower limit which are determined by a standard deviation value calculated from the sampling data at each sampling point, to thereby monitor the machining process. Determination as to defective/non-defective is performed at each sampling point on the basis of the range between the upper and lower limits which model the shape of the work. As a result, the probability of non-defective products being unretrieved as data is reduced and abnormalities are detected quickly at each sampling point to allow swift handling of the problem.

摘要翻译： 公开了一种用于机床的监控装置，其监视加工中的操作以提高工件的产量的精确度。 为了以从加工开始到加工结束运行的1个循环单位来监控供给加工电机的负载电流，在机加工的区域沿着加工的时间轴以更短的间隔采取采样点 复杂，并且在加工简单的区域中，沿着加工的时间轴以更长的间隔采取采样点; 并且在每个采样点，采样数据被存储并进行数字处理。 然后，比较负载电流的实际测量值，以确定实际测量值是否在由每个采样点的采样数据计算的标准偏差值确定的上限和下限的范围内， 从而监控加工过程。 根据对作品形状进行建模的上限和下限之间的范围，在每个采样点进行有缺陷/无缺陷的判定。 结果，随着数据的减少，无缺陷产品的概率不断下降，并且在每个采样点快速检测到异常，以便迅速处理该问题。