公开(公告)号：US20160012577A1

公开(公告)日：2016-01-14

申请号：US14845605

申请日：2015-09-04

申请人： OMRON Corporation

发明人： Minoru OKA ,  Shinya SAWA

IPC分类号： G06T7/00 ,  G05B19/05 ,  G06F17/30

CPC分类号： G06T7/0004 ,  G05B19/05 ,  G05B19/41875 ,  G05B19/4188 ,  G05B2219/31323 ,  G05B2219/32186 ,  G05B2219/37028 ,  G06F17/3028 ,  G06T2207/30164 ,  Y02P90/22 ,  Y02P90/24 ,  Y02P90/265

摘要： A control system configured to use a database and a data storage area includes a control device for controlling a process executed on an object; and an image processing device arranged in association with the control device for taking an image of the object and processing image data acquired from taking the image of the object. The control device and the image processing device may work independently or collaboratively to send the database at least one of an attribute value or results information, and designation information in association with each other for the same object, the attribute value managed by the control device and corresponding to any attribute defined in the database, the results information representing a process result from the image processing device, and the designation information specifying a storage destination in the data storage area for the image data acquired from taking an image of the object.

摘要翻译： 配置为使用数据库和数据存储区域的控制系统包括用于控制对象上执行的处理的控制装置; 以及图像处理装置，其与所述控制装置相关联地设置，用于拍摄所述对象的图像，并且处理从拍摄对象的图像获取的图像数据。 控制装置和图像处理装置可以独立地或协作地为同一对象相关联地发送属性值或结果信息以及指定信息中的至少一个，由控制装置管理的属性值和 对应于数据库中定义的任何属性，表示来自图像处理装置的处理结果的结果信息，以及指定用于从获取对象的图像获取的图像数据的数据存储区域中的存储目的地的指定信息。

公开(公告)号：US20090281755A1

公开(公告)日：2009-11-12

申请号：US12430701

申请日：2009-04-27

申请人： Tomohiro Funakoshi

发明人： Tomohiro Funakoshi

IPC分类号： G06F19/00

CPC分类号： G05B19/41875 ,  G01R31/2894 ,  G05B2219/32186 ,  G05B2219/37224 ,  Y02P90/20 ,  Y02P90/22

摘要： In operation to obtain an optimal observation condition in a review system, the number of trial reviews can be reduced to improve efficiency of the operation. For a defect review conducted by the review system, a recipe parameter management system stores, as recipe parameter setting history in a recipe parameter setting history DB, recipe parameter setting values of recipe parameters set when the defect review is conducted, the number of trial reviews carried out until the recipe parameter setting values are set, and defect images obtained when the defect review is conducted. The apparatus displays, on a terminal, histograms and the numbers of trial reviews generated based on the recipe parameter setting history data stored in the recipe parameter setting history DB. Hence, the operator can easily obtain data regarding the recipe parameter setting in the past.

摘要翻译： 在审查系统中获得最佳观察条件的操作中，可以减少审查次数以提高操作效率。 对于由检查系统进行的缺陷检查，配方参数管理系统将作为配方参数设置历史DB中的配方参数设置历史存储在进行缺陷检查时设定的配方参数的配方参数设定值，审查次数 进行到配方参数设定值的设定，进行缺陷检查时获得的缺陷图像。 该装置在终端上显示基于存储在配方参数设置历史DB中的食谱参数设置历史数据生成的直方图和试验评价的数量。 因此，操作者可以容易地获得关于过去配方参数设置的数据。

公开(公告)号：US5542600A

公开(公告)日：1996-08-06

申请号：US232022

申请日：1994-04-26

申请人： Shigeki Kobayashi ,  Norihito Yamamoto

发明人： Shigeki Kobayashi ,  Norihito Yamamoto

IPC分类号： B23K1/00 ,  B23K3/03 ,  B23K3/08 ,  B25J9/16 ,  G05B19/418 ,  H05K13/04 ,  H05K13/08 ,  B23K1/19

CPC分类号： H05K13/0486 ,  B23K1/0016 ,  B23K3/033 ,  B23K3/08 ,  B25J9/16 ,  G05B19/41865 ,  G05B19/41875 ,  G05B19/41885 ,  H05K13/08 ,  B23K2201/42 ,  G05B2219/31096 ,  G05B2219/31296 ,  G05B2219/31355 ,  G05B2219/31446 ,  G05B2219/32121 ,  G05B2219/32127 ,  G05B2219/32145 ,  G05B2219/32146 ,  G05B2219/32147 ,  G05B2219/32148 ,  G05B2219/32151 ,  G05B2219/32173 ,  G05B2219/32174 ,  G05B2219/32175 ,  G05B2219/32186 ,  G05B2219/32192 ,  G05B2219/32229 ,  G05B2219/32231 ,  G05B2219/32232 ,  G05B2219/45235 ,  G05B2219/50064 ,  Y02P90/04 ,  Y02P90/10 ,  Y02P90/20 ,  Y02P90/22 ,  Y02P90/26 ,  Y02P90/265

摘要： Soldering condition information such as the position and angle of a soldering iron, amount of solder supplied and heating time is stored beforehand, for each grouping of parts, in a part classification table (26) for soldering purposes. Parts to be mounted on a board are stored, in correspondence with the board ID, on a floppy disk of a floppy disk device (24). When the board ID is entered, the parts to be mounted on the board are displayed on a display unit (23). The operator reads out the part classification table (26) for soldering purposes and designates soldering correction information that corresponds to the part groups to which the parts belong. As a result, a teach-data table (27) in which soldering condition information has been stored in correspondence with the parts is created. Soldering is executed automatically in accordance with the teach-data table (27).

摘要翻译： PCT No.PCT / JP92 / 01448 Sec。 371日期1994年04月26日 102（e）日期1994年4月26日PCT提交1992年11月9日PCT公布。 出版物WO93 / 09654 日期1993年5月13日焊接条件信息如烙铁的位置和角度，供应的焊料量和加热时间预先存储在用于焊接目的的部件分类表（26）中。 将要安装在板上的部件与板ID相对应地存储在软盘设备（24）的软盘上。 当输入板ID时，将要安装在板上的部件显示在显示单元（23）上。 操作人员为了焊接目的读出零件分类表（26），并指定与零件所属部件组对应的焊接修正信息。 结果，产生了与部件对应地存储焊接条件信息的教学数据表（27）。 根据教学数据表（27）自动执行焊接。

公开(公告)号：US20190243346A1

公开(公告)日：2019-08-08

申请号：US16389083

申请日：2019-04-19

申请人： International Business Machines Corporation

发明人： Robert J. Baseman ,  Jayant R. Kalagnanam ,  Young M. Lee ,  Jie Ma ,  Jian Wang ,  Guan Qun Zhang

IPC分类号： G05B19/418 ,  G05B13/02

CPC分类号： G05B19/4188 ,  G05B13/0265 ,  G05B19/41875 ,  G05B2219/32186 ,  G05B2219/33034 ,  G05B2219/42001 ,  Y02P90/02

摘要： Controlling product production in multi-stage manufacturing process automatically generates by machine learning causal relationships between the processing conditions and the product quality based on product genealogy data and product quality data. Real time sensor data from sensors coupled to processing units in a manufacturing facility implementing the multi-stage manufacturing process are received, and control rules are instantiated based on the real time sensor data. An instantiated control rule firing causes an actuator to automatically set a processing variable to a set point specified in the control rule.

公开(公告)号：US20190223337A1

公开(公告)日：2019-07-18

申请号：US16161088

申请日：2018-10-16

申请人： OMRON Corporation

发明人： Hiroyuki MORI ,  Katsuki NAKAJIMA ,  Takako ONISHI ,  Isao NAKANISHI ,  Mayuko TANAKA

IPC分类号： H05K13/08 ,  G01N21/956 ,  G01N23/083

CPC分类号： G05B19/41875 ,  G05B2219/32186 ,  G05B2219/32196 ,  G05B2219/32197 ,  H05K13/083

摘要： An inspection management system having a plurality of processes and managing final inspection performed to inspect a completed product and one or more intermediate inspections performed to inspect an intermediate product manufactured in the processes earlier than a final process includes: an inspection content data acquisition unit that acquires inspection content data including an inspection standard for each inspection item of the product; an inspection content setting unit that sets inspection content based on the inspection content data acquired by the inspection content data acquisition unit; a simulation unit that simulates inspection in accordance with assumed inspection content; an inspection standard calculation unit that calculates an inspection standard more appropriate than a current inspection standard based on the simulation; and an output unit that outputs base information indicating that at least the inspection standard calculated by the inspection standard calculation unit is more appropriate than the current inspection standard.

公开(公告)号：US08131020B2

公开(公告)日：2012-03-06

申请号：US11596429

申请日：2005-05-18

申请人： John F. Macgregor ,  Jay J. Liu

发明人： John F. Macgregor ,  Jay J. Liu

IPC分类号： G06K9/00

CPC分类号： G05B13/048 ,  G01N21/8851 ,  G01N2021/8887 ,  G05B19/41875 ,  G05B2219/32186 ,  G06T7/0004 ,  G06T7/0006 ,  G06T7/42 ,  G06T2207/20064 ,  G06T2207/30164 ,  Y02P90/22 ,  Y02P90/26

摘要： A new application of machine vision for process industries is proposed. The invention consists of: (1) estimation of visual quality of products, (2) modeling causal relationship between estimated quality and process variables, and (3) optimization of visual quality using the causal model. This invention can handle the stochastic nature in visual appearance of products that process industries provide, which has been a main obstacle for the success of machine vision in process industries. Also, it opens new tasks in machine vision such as modeling and optimization of visual quality of products.

摘要翻译： 提出了加工工业机器视觉的新应用。 本发明包括：（1）产品视觉质量的估计，（2）估计质量与过程变量之间的因果关系建模，（3）使用因果模型优化视觉质量。 本发明可以处理工艺行业提供的产品的视觉外观随机性，这是加工行业机器视觉成功的主要障碍。 此外，它开启了机器视觉的新任务，如产品视觉质量的建模和优化。

公开(公告)号：US20080013821A1

公开(公告)日：2008-01-17

申请号：US11596429

申请日：2005-05-18

申请人： John Macgregor ,  Jay Liu

发明人： John Macgregor ,  Jay Liu

IPC分类号： G06K9/00

CPC分类号： G05B13/048 ,  G01N21/8851 ,  G01N2021/8887 ,  G05B19/41875 ,  G05B2219/32186 ,  G06T7/0004 ,  G06T7/0006 ,  G06T7/42 ,  G06T2207/20064 ,  G06T2207/30164 ,  Y02P90/22 ,  Y02P90/26

摘要： A new application of machine vision for process industries is proposed. The invention consists of: (1) estimation of visual quality of products, (2) modeling causal relationship between estimated quality and process variables, and (3) optimization of visual quality using the causal model. This invention can handle the stochastic nature in visual appearance of products that process industries provide, which has been a main obstacle for the success of machine vision in process industries. Also, it opens new tasks in machine vision such as modeling and optimization of visual quality of products.

摘要翻译： 提出了加工工业机器视觉的新应用。 本发明包括：（1）产品视觉质量的估计，（2）估计质量与过程变量之间的因果关系建模，（3）使用因果模型优化视觉质量。 本发明可以处理工艺行业提供的产品的视觉外观随机性，这是加工行业机器视觉成功的主要障碍。 此外，它开启了机器视觉的新任务，如产品视觉质量的建模和优化。

公开(公告)号：US20180292812A1

公开(公告)日：2018-10-11

申请号：US15806591

申请日：2017-11-08

申请人： International Business Machines Corporation

发明人： Robert J. Baseman ,  Jayant R. Kalagnanam ,  Young M. Lee ,  Jie Ma ,  Jian Wang ,  Guan Qun Zhang

IPC分类号： G05B19/418 ,  G05B13/02

CPC分类号： G05B19/4188 ,  G05B13/0265 ,  G05B19/41875 ,  G05B2219/32186 ,  G05B2219/33034 ,  G05B2219/42001 ,  Y02P90/02

摘要： Controlling product production in multi-stage manufacturing process automatically generates by machine learning causal relationships between the processing conditions and the product quality based on product genealogy data and product quality data. Real time sensor data from sensors coupled to processing units in a manufacturing facility implementing the multi-stage manufacturing process are received, and control rules are instantiated based on the real time sensor data. An instantiated control rule firing causes an actuator to automatically set a processing variable to a set point specified in the control rule.

公开(公告)号：US07627392B2

公开(公告)日：2009-12-01

申请号：US11848214

申请日：2007-08-30

申请人： Wei Liu ,  Shifang Li ,  Weidung Yang ,  Manuel Madriaga

发明人： Wei Liu ,  Shifang Li ,  Weidung Yang ,  Manuel Madriaga

IPC分类号： G06F19/00

CPC分类号： G05B19/41875 ,  G01N21/4788 ,  G03F7/70625 ,  G05B2219/32182 ,  G05B2219/32186 ,  G05B2219/32188 ,  G05B2219/37224

摘要： Provided is a method of controlling a fabrication cluster using a machine learning system, the machine learning system trained developed using an optical metrology model. A simulated approximation diffraction signal is generated based on an approximation diffraction model of the structure. A set of difference diffraction signal is obtained by subtracting the simulated approximation diffraction signal from each of simulated fine diffraction signals and paired with the corresponding profile parameters. A first machine learning system is trained using the pairs of difference diffraction signal and corresponding profile parameters. A library of simulated fine diffraction signals and profile parameters is generated using the trained first machine learning system and using ranges and corresponding resolutions of the profile parameters. A measured diffraction signal is input into the trained second machine learning system to determine at least one profile parameter. The at least one profile parameter is used to adjust at least one process parameter or equipment setting of the fabrication cluster.

摘要翻译： 提供了一种使用机器学习系统来控制制造集群的方法，使用光学计量学模型训练的机器学习系统。 基于结构的近似衍射模型生成模拟近似衍射信号。 通过从每个模拟的细衍射信号中减去模拟近似衍射信号并与相应的轮廓参数配对来获得差分衍射信号。 使用差分衍射信号和相应的轮廓参数对来训练第一机器学习系统。 使用训练有素的第一机器学习系统并使用轮廓参数的范围和相应的分辨率来生成模拟的细衍射信号和轮廓参数的库。 测量的衍射信号被输入到训练有素的第二机器学习系统中以确定至少一个轮廓参数。 至少一个轮廓参数用于调整至少一个制造集群的过程参数或设备设置。

公开(公告)号：US07324863B2

公开(公告)日：2008-01-29

申请号：US11394286

申请日：2006-03-30

申请人： Paul P. Thirumalai ,  Rick Mayer ,  Mike J. Wodarczyk

发明人： Paul P. Thirumalai ,  Rick Mayer ,  Mike J. Wodarczyk

IPC分类号： G06F19/00

CPC分类号： G05B19/41875 ,  G05B2219/32186 ,  G05B2219/32206 ,  G05B2219/45031 ,  Y02P90/22

摘要： In one embodiment, the present invention includes a method for receiving a set of inspection files each corresponding to an inspection performed on a wafer of a set of wafers, automatically analyzing the set of inspection files to select at least one inspection file corresponding to a predetermined rule set, and identifying the wafer(s) associated with the selected inspection file(s). Other embodiments are described and claimed.

摘要翻译： 在一个实施例中，本发明包括一种用于接收一组检查文件的方法，每个检查文件对应于在一组晶片的晶片上进行的检查，自动分析检查文件集合，以选择至少一个与预定的 规则集，以及识别与所选择的检查文件相关联的晶片。 描述和要求保护其他实施例。