公开(公告)号：US11074522B2

公开(公告)日：2021-07-27

申请号：US16916013

申请日：2020-06-29

申请人： Roger N. Anderson ,  Boyi Xie ,  Leon L. Wu ,  Arthur Kressner

发明人： Roger N. Anderson ,  Boyi Xie ,  Leon L. Wu ,  Arthur Kressner

IPC分类号： G06N20/00

摘要： Electric Grid Analytics Learning Machine, EGALM, is a machine learning based, “brutally empirical” analysis system for use in all energy operations. EGALM is applicable to all aspects of the electricity operations from power plants to homes and businesses. EGALM is a data-centric, computational learning and predictive analysis system that uses open source algorithms and unique techniques applicable to all electricity operations in the United States and other foreign countries.

公开(公告)号：US20090157573A1

公开(公告)日：2009-06-18

申请号：US12178553

申请日：2008-07-23

申请人： Roger N. Anderson ,  Albert Boulanger ,  David L. Waltz ,  Phil Long ,  Arias Marta ,  Philip Gross ,  Hila Becker ,  Arthur Kressner ,  Mark Mastrocinque ,  Matthew Koenig ,  John A. Johnson

发明人： Roger N. Anderson ,  Albert Boulanger ,  David L. Waltz ,  Phil Long ,  Arias Marta ,  Philip Gross ,  Hila Becker ,  Arthur Kressner ,  Mark Mastrocinque ,  Matthew Koenig ,  John A. Johnson

IPC分类号： G06F15/18

CPC分类号： G06N99/005

摘要： A machine learning system creates failure-susceptibility rankings for feeder cables in a utility's electrical distribution system. The machine learning system employs martingale boosting algorithms and Support Vector Machine (SVM) algorithms to generate a feeder failure prediction model, which is trained on static and dynamic feeder attribute data. Feeders are dynamically ranked by failure susceptibility and the rankings displayed to utility operators and engineers so that they can proactively service the distribution system to prevent local power outages. The feeder rankings may be used to redirect power flows and to prioritize repairs. A feedback loop is established to evaluate the responses of the electrical distribution system to field actions taken to optimize preventive maintenance programs.

摘要翻译： 机器学习系统为公用事业的配电系统中的馈线电缆创建故障敏感性排名。 机器学习系统采用mart升级算法和支持向量机（SVM）算法，生成馈线故障预测模型，对静态和动态馈线属性数据进行了培训。 馈线由故障敏感性和对公用事业运营商和工程师的排名进行动态排名，以便他们可以主动为服务分配系统，以防止局部停电。 馈线排名可用于重定向电力流量并优先进行维修。 建立了一个反馈回路，以评估配电系统对优化预防性维护计划所采取的现场行动的响应。

公开(公告)号：US07945524B2

公开(公告)日：2011-05-17

申请号：US12178553

申请日：2008-07-23

申请人： Roger N. Anderson ,  Albert Boulanger ,  David L. Waltz ,  Phil Long ,  Marta Arias ,  Philip Gross ,  Hila Becker ,  Arthur Kressner ,  Mark Mastrocinque ,  Matthew Koenig ,  John A. Johnson

发明人： Roger N. Anderson ,  Albert Boulanger ,  David L. Waltz ,  Phil Long ,  Marta Arias ,  Philip Gross ,  Hila Becker ,  Arthur Kressner ,  Mark Mastrocinque ,  Matthew Koenig ,  John A. Johnson

IPC分类号： G06F15/18

CPC分类号： G06N99/005

摘要： A machine learning system creates failure-susceptibility rankings for feeder cables in a utility's electrical distribution system. The machine learning system employs martingale boosting algorithms and Support Vector Machine (SVM) algorithms to generate a feeder failure prediction model, which is trained on static and dynamic feeder attribute data. Feeders are dynamically ranked by failure susceptibility and the rankings displayed to utility operators and engineers so that they can proactively service the distribution system to prevent local power outages. The feeder rankings may be used to redirect power flows and to prioritize repairs. A feedback loop is established to evaluate the responses of the electrical distribution system to field actions taken to optimize preventive maintenance programs.

摘要翻译： 机器学习系统为公用事业的配电系统中的馈线电缆创建故障敏感性排名。 机器学习系统采用mart升级算法和支持向量机（SVM）算法，生成馈线故障预测模型，对静态和动态馈线属性数据进行了培训。 馈线由故障敏感性和对公用事业运营商和工程师的排名进行动态排名，以便他们可以主动为服务分配系统，以防止局部停电。 馈线排名可用于重定向电力流量并优先进行维修。 建立了一个反馈回路，以评估配电系统对优化预防性维护计划所采取的现场行动的响应。

公开(公告)号：US20130073488A1

公开(公告)日：2013-03-21

申请号：US13589737

申请日：2012-08-20

申请人： Roger N. Anderson ,  Albert Boulanger ,  Leon L. Wu

发明人： Roger N. Anderson ,  Albert Boulanger ,  Leon L. Wu

IPC分类号： G06F15/18

CPC分类号： G06Q10/04

摘要： Techniques for evaluating the accuracy of a predicted effectiveness of an improvement to an infrastructure include collecting data, representative of at least one pre-defined metric, from the infrastructure during first and second time periods corresponding to before and after a change has been implemented, respectively. A machine learning system can receive compiled data representative of the first time period and generate corresponding machine learning data. A machine learning results evaluator can empirically analyze the generated machine learning data. An implementer can implement the change to the infrastructure based at least in part on the data from a machine learning data outputer. A system performance improvement evaluator can compare the compiled data representative of the first time period to that of the second time period to determine a difference, if any, and compare the difference, if any, to a prediction based on the generated machine learning data.

摘要翻译： 用于评估对基础设施改进的预测有效性的准确性的技术包括分别在对应于改变之前和之后的第一和第二时间段期间从基础设施收集表示至少一个预定义度量的数据 。 机器学习系统可以接收代表第一时间段的编译数据并产生相应的机器学习数据。 机器学习结果评估器可以经验性地分析生成的机器学习数据。 至少部分地基于来自机器学习数据输出器的数据，实现者可以实现对基础设施的改变。 系统性能改进评估器可以将表示第一时间段的编译数据与第二时间周期的编译数据进行比较，以确定差异（如果有的话），并根据所生成的机器学习数据将差值（如果有的话）与预测进行比较。

公开(公告)号：US08725665B2

公开(公告)日：2014-05-13

申请号：US13589737

申请日：2012-08-20

申请人： Roger N. Anderson ,  Albert Boulanger ,  Leon Wu ,  Serena Lee

发明人： Roger N. Anderson ,  Albert Boulanger ,  Leon Wu ,  Serena Lee

IPC分类号： G06F15/18

CPC分类号： G06Q10/04

摘要： Techniques for evaluating the accuracy of a predicted effectiveness of an improvement to an infrastructure include collecting data, representative of at least one pre-defined metric, from the infrastructure during first and second time periods corresponding to before and after a change has been implemented, respectively. A machine learning system can receive compiled data representative of the first time period and generate corresponding machine learning data. A machine learning results evaluator can empirically analyze the generated machine learning data. An implementer can implement the change to the infrastructure based at least in part on the data from a machine learning data outputer. A system performance improvement evaluator can compare the compiled data representative of the first time period to that of the second time period to determine a difference, if any, and compare the difference, if any, to a prediction based on the generated machine learning data.

摘要翻译： 用于评估对基础设施改进的预测有效性的准确性的技术包括分别在对应于改变之前和之后的第一和第二时间段期间从基础设施收集表示至少一个预定义度量的数据 。 机器学习系统可以接收代表第一时间段的编译数据并产生相应的机器学习数据。 机器学习结果评估器可以经验性地分析生成的机器学习数据。 至少部分地基于来自机器学习数据输出器的数据，实现者可以实现对基础设施的改变。 系统性能改进评估器可以将表示第一时间段的编译数据与第二时间周期的编译数据进行比较，以确定差异（如果有的话），并根据生成的机器学习数据将差值（如果有的话）与预测进行比较。

公开(公告)号：US08560476B2

公开(公告)日：2013-10-15

申请号：US12019347

申请日：2008-01-24

申请人： Roger N. Anderson ,  Albert Boulanger ,  Wei He ,  Ulisses Mello ,  Liqing Xu

发明人： Roger N. Anderson ,  Albert Boulanger ,  Wei He ,  Ulisses Mello ,  Liqing Xu

IPC分类号： G06F17/00 ,  G06N5/00 ,  G06G7/48

CPC分类号： G01V11/00 ,  G01V2210/612 ,  G06Q10/04

摘要： A computer-aided lean management (CALM) controller system recommends actions and manages production in an oil and gas reservoir/field as its properties and conditions change with time. The reservoir/field is characterized and represented as an electronic-field (“e-field”). A plurality of system applications describe dynamic and static e-field properties and conditions. The application workflows are integrated and combined in a feedback loop between actions taken in the field and metrics that score the success or failure of those actions. A controller/optimizer operates on the combination of the application workflows to compute production strategies and actions. The controller/optimizer is configured to generate a best action sequence for production, which is economically “always-in-the-money.”

摘要翻译： 计算机辅助精简管理（CALM）控制器系统建议在油气藏/油田中的生产进行动作和管理，因为其属性和条件随时间而变化。 水库/油田被表征为电子场（“电场”）。 多个系统应用程序描述动态和静态电场特性和条件。 应用程序工作流程被集成在一起，并结合在现场采取的动作和衡量这些操作的成功或失败的指标之间的反馈循环中。 一个控制器/优化器运行在应用程序工作流的组合上来计算生产策略和动作。 控制器/优化器被配置为生成最佳的动作序列，这是经济上“永远在金钱”。

公开(公告)号：US20100071622A1

公开(公告)日：2010-03-25

申请号：US12234038

申请日：2008-09-19

申请人： DAVID K. CARLSON ,  Roger N. Anderson

发明人： DAVID K. CARLSON ,  Roger N. Anderson

IPC分类号： B05D5/00 ,  B32B27/04 ,  B32B9/00

CPC分类号： C23C30/00 ,  B05D5/083 ,  B05D7/14 ,  B05D2350/65 ,  C23C2/26 ,  C23C26/00 ,  C23C28/00 ,  Y10T428/239 ,  Y10T428/263 ,  Y10T428/264 ,  Y10T428/265 ,  Y10T428/3154

摘要： A method of treating a metal surface of a portion of a substrate processing system to lower a defect concentration near a processed surface of a substrate includes forming a protective coating on the metal surface, wherein the protective coating includes nickel (Ni) and a fluoropolymer. Forming the protective coating on the metal surface can further include forming a nickel layer on the metal surface, impregnating the nickel layer with a fluoropolymer, and removing fluoropolymer from the surface leaving a predominantly nickel surface so the fluoropolymer is predominantly subsurface. A substrate processing system includes a process chamber into which a reactant gas is introduced, a pumping system for removing material from the process chamber, a first component with a protective coating, wherein the protective coating forms a surface of the component which is exposed to an interior of the substrate processing chamber or an interior of the pumping system. The protective coating includes nickel (Ni) and a flouropolymer.

摘要翻译： 处理基板处理系统的一部分的金属表面以降低基板的加工表面附近的缺陷浓度的方法包括在金属表面上形成保护涂层，其中保护涂层包括镍（Ni）和含氟聚合物。 在金属表面上形成保护涂层还可以包括在金属表面上形成镍层，用含氟聚合物浸渍镍层，以及从表面除去含氟聚合物，留下主要的镍表面，因此含氟聚合物主要是在下表面。 基板处理系统包括其中引入反应气体的处理室，用于从处理室中去除材料的泵送系统，具有保护涂层的第一部件，其中所述保护涂层形成暴露于所述部件的表面 衬底处理室的内部或泵送系统的内部。 保护涂层包括镍（Ni）和氟聚合物。

公开(公告)号：US20090194026A1

公开(公告)日：2009-08-06

申请号：US12023572

申请日：2008-01-31

申请人： BRIAN H. BURROWS ,  Lori D. Washington ,  Ronald Stevens ,  Kenric T. Choi ,  Anthony F. White ,  Roger N. Anderson ,  Sandeep Nijhawan ,  Joshua J. Podesta ,  Alexander Tam

发明人： BRIAN H. BURROWS ,  Lori D. Washington ,  Ronald Stevens ,  Kenric T. Choi ,  Anthony F. White ,  Roger N. Anderson ,  Sandeep Nijhawan ,  Joshua J. Podesta ,  Alexander Tam

IPC分类号： C23C16/54

CPC分类号： C23C16/54 ,  C30B25/08 ,  C30B29/403 ,  C30B35/00 ,  H01L21/67017 ,  H01L21/67115 ,  H01L21/67161 ,  H01L21/67207 ,  H01L21/68764 ,  H01L21/68771

摘要： One embodiment of a processing system for fabricating compound nitride semiconductor devices comprises one or more processing chamber operable with form a compound nitride semiconductor layer on a substrate, a transfer chamber coupled with the processing chamber, a loadlock chamber coupled with the transfer chamber, and a load station coupled with the loadlock chamber, wherein the load station comprises a conveyor tray movable to convey a carrier plate loaded with one or more substrates into the loadlock chamber. Compared to a single chamber reactor, the multi-chamber processing system expands the potential complexity and variety of compound structures. Additionally, the system can achieve higher quality and yield by specialization of individual chambers for specific epitaxial growth processes. Throughput is increased by simultaneous processing in multiple chambers.

摘要翻译： 用于制造复合氮化物半导体器件的处理系统的一个实施例包括可在衬底上形成复合氮化物半导体层的可操作的一个或多个处理室，与处理室耦合的传送室，与传送室耦合的负载锁定室，以及 加载站与负载锁定室耦合，其中装载站包括可移动以将装载有一个或多个基板的承载板输送到负载锁定室中的输送器托盘。 与单室反应器相比，多室处理系统扩大了复合结构的潜在复杂性和多样性。 此外，该系统可以通过专用于特定外延生长工艺的各个室来实现更高的质量和产量。 通过在多个室中同时处理来提高吞吐量。

公开(公告)号：US20080294387A1

公开(公告)日：2008-11-27

申请号：US12019347

申请日：2008-01-24

申请人： Roger N. Anderson ,  Albert Boulanger ,  Wei He ,  Ulisses Mello ,  Liqing Xu

发明人： Roger N. Anderson ,  Albert Boulanger ,  Wei He ,  Ulisses Mello ,  Liqing Xu

IPC分类号： G06F17/50 ,  G06G7/50

CPC分类号： G01V11/00 ,  G01V2210/612 ,  G06Q10/04

摘要： A computer-aided lean management (CALM) controller system recommends actions and manages production in an oil and gas reservoir/field as its properties and conditions change with time. The reservoir/field is characterized and represented as an electronic-field (“e-field”). A plurality of system applications describe dynamic and static e-field properties and conditions. The application workflows are integrated and combined in a feedback loop between actions taken in the field and metrics that score the success or failure of those actions. A controller/optimizer operates on the combination of the application workflows to compute production strategies and actions. The controller/optimizer is configured to generate a best action sequence for production, which is economically “always-in-the-money.”

摘要翻译： 计算机辅助精简管理（CALM）控制器系统建议在油气藏/油田中的生产进行动作和管理，因为其属性和条件随时间而变化。 水库/油田被表征为电子场（“电场”）。 多个系统应用程序描述动态和静态电场特性和条件。 应用程序工作流程被集成在一起，并结合在现场采取的动作和衡量这些操作的成功或失败的指标之间的反馈循环中。 一个控制器/优化器运行在应用程序工作流的组合上来计算生产策略和动作。 控制器/优化器被配置为生成最佳的动作序列，这是经济上“永远在金钱”。

公开(公告)号：US6146464A

公开(公告)日：2000-11-14

申请号：US884243

申请日：1997-06-30

申请人： Israel Beinglass ,  Mahalingam Venkatesan ,  Roger N. Anderson

发明人： Israel Beinglass ,  Mahalingam Venkatesan ,  Roger N. Anderson

IPC分类号： H01L21/687 ,  C23C16/00

CPC分类号： H01L21/6875 ,  H01L21/68735

摘要： An apparatus for depositing a material on a wafer includes a susceptor plate mounted in a deposition chamber. The chamber has a gas inlet and a gas exhaust. Means are provided for heating the susceptor plate. The susceptor plate has a plurality of support posts projecting from its top surface. The support posts are arranged to support a wafer thereon with the back surface of the wafer being spaced from the surface of the susceptor plate. The support posts are of a length so that the wafer is spaced from the susceptor plate a distance sufficient to allow deposition gas to flow and/or diffuse between the wafer and the susceptor plate, but still allow heat transfer from the susceptor plate to the wafer mainly by conduction. The susceptor plate is also provided with means, such as retaining pins or a recess, to prevent lateral movement of a wafer seated on the support posts.

摘要翻译： 用于在晶片上沉积材料的设备包括安装在沉积室中的基座板。 该室具有气体入口和排气。 提供用于加热感受板的装置。 基座板具有从其顶表面突出的多个支撑柱。 支撑柱布置成在其上支撑晶片，其中晶片的后表面与基座板的表面间隔开。 支撑柱具有长度，使得晶片与基座板间隔足以允许沉积气体在晶片和基座板之间流动和/或扩散的距离，但仍允许从基座板到晶片的热传递 主要是通过传导。 基座板还设置有诸如保持销或凹部的装置，以防止位于支撑柱上的晶片的横向移动。