中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

31 records (took 0.017 seconds)

    SYSTEMS AND METHOD FOR DYNAMIC COMBUSTION TESTS
    12.
    发明申请
    SYSTEMS AND METHOD FOR DYNAMIC COMBUSTION TESTS 审中-公开

    公开(公告)号：US20180246504A1

    公开(公告)日：2018-08-30

    申请号：US15445334

    申请日：2017-02-28

    Applicant: General Electric Company

    Inventor： Liping Wang ,  Isaac Mendel Asher ,  You Ling ,  Ankur Srivastava ,  Arun Karthi Subramaniyan

    IPC: G05B23/00 ,  G06F17/30 ,  G06F17/50

    Abstract: A testing system computer device for dynamically updating a test plan of an apparatus includes at least one processor in communication with at least one memory device. The testing system computer device is configured to store a plurality of historical data and generate a simulation model of the apparatus based in part on the historical data. The simulation model includes a plurality of inputs and a plurality of outputs of the apparatus. The testing system computer device is also configured to determine a plurality of tests to perform on the apparatus based on the simulation model and the plurality of historical data. The testing system computer device is further configured to receive a plurality of desirability ratings from a user, rank the plurality of tests to perform based on the plurality of desirability ratings, and present the ranked plurality of tests to the user.

    Scalable and secure analytic model integration and deployment platform
    15.
    发明授权
    Scalable and secure analytic model integration and deployment platform 有权

    公开(公告)号：US10127027B2

    公开(公告)日：2018-11-13

    申请号：US15338951

    申请日：2016-10-31

    Applicant: General Electric Company

    Inventor： Arun Karthi Subramaniyan ,  Alexandre Iankoulski ,  John Lazos

    IPC: G06F9/46 ,  G06F8/60 ,  G06F9/455

    Abstract: According to some embodiments, system, apparatus and methods are provided comprising an analytic model for an installed product; an execution platform configured to execute the analytic model; an application programming interface (API) wrapper associated with each of the analytic model and the execution platform, the API wrapper including input information, output information and a technique; and a storage in communication with the analytic model and the execution platform and storing program instructions to perform the functions as follows: transmitting information between the analytic API wrapper and the execution platform API wrapper; and deploying the analytic model to the execution platform based on the transmitted information. Numerous other aspects are provided.

    SYSTEMS AND METHODS FOR DATA ESTIMATION AND FORECASTING
    16.
    发明申请
    SYSTEMS AND METHODS FOR DATA ESTIMATION AND FORECASTING 审中-公开

    公开(公告)号：US20170193381A1

    公开(公告)日：2017-07-06

    申请号：US14986211

    申请日：2015-12-31

    Applicant: General Electric Company

    Inventor： Arun Karthi Subramaniyan ,  Felipe Antonio Chegury Viana ,  Fabio Nontao de Paula ,  Natarajan Chennimalai Kumar

    IPC: G06N7/00 ,  G06F17/30

    CPC classification number: G06N7/005 ,  G06F17/18

    Abstract: A system for estimating data in large datasets for an equipment system is provided. The system includes a data estimation and forecasting (DEF) computing device. The DEF computing device arranges a dataset in a primary matrix and parses rows of the primary matrix and generates a sample matrix by selecting primary matrix rows having non-null values for each variable. The DEF computing device adds to the sample matrix rows that include non-null values for each variable except one. The DEF computing device generates normalized values for this augmented matrix, applies several techniques including probabilistic principal component analysis (PPCA) and Markov processes, and scales the augmented matrix to normalized values. The DEF computing device generates non-null values for the variable, scales the augmented matrix back to the sample matrix, and generates a forecast for the equipment system, directing a user to update logistics processes for the equipment system.

    Probabilistic method and system for testing a material
    18.
    发明授权
    Probabilistic method and system for testing a material 有权
    用于材料测试的概率法和系统

    公开(公告)号：US09245067B2

    公开(公告)日：2016-01-26

    申请号：US13840785

    申请日：2013-03-15

    Applicant: General Electric Company

    Inventor： Arun Karthi Subramaniyan ,  Shesh Krishna Srivatsa ,  Don Beeson ,  Liping Wang

    IPC: G06G7/48 ,  G06F17/50

    CPC classification number: G06F17/5009

    Abstract: A method implemented using a processor based device for simulation based testing of materials, includes selecting a first set of points from a data generated from a design space and generating a stochastic metamodel based on the first set of points. The method also includes determining an uncertainty value based on the stochastic metamodel. The method also includes identifying a second set of points different from the first set of points, from the data generated from the design space, based on the uncertainty value. The method further includes combining the second set of points with the first set of points to generate a third set of points, assigning the third set of points to the first set of points. The method also includes iteratively generating, determining, identifying, combining, and assigning steps till the uncertainty value is less than or equal to a predetermined threshold value.

    Abstract translation: 使用基于处理器的设备实现的用于对材料进行基于模拟的测试的方法包括从从设计空间生成的数据中选择第一组点，并基于第一组点生成随机元模型。 该方法还包括基于随机元模型来确定不确定性值。 该方法还包括基于不确定性值从与设计空间生成的数据中识别不同于第一组点的第二组点。 该方法还包括将第二组点与第一组点组合以产生第三组点，将第三组点分配给第一组点。 该方法还包括迭代地生成，确定，识别，组合和分配步骤，直到不确定性值小于或等于预定阈值。

    Massively accelerated Bayesian machine
    19.
    发明授权
    Massively accelerated Bayesian machine 有权

    公开(公告)号：US10719639B2

    公开(公告)日：2020-07-21

    申请号：US15401746

    申请日：2017-01-09

    Applicant: General Electric Company

    Inventor： Felipe Antonio Chegury Viana ,  Arun Karthi Subramaniyan

    IPC: G06N7/00 ,  G06F30/20

    Abstract: According to some embodiments, system and methods are provided comprising: receiving data; providing a simulation model for the data; generating one or more simulations via a Bayesian module based on the data, wherein the simulation includes one or more nodes in a chain; executing the Bayesian module to determine the acceptability of the nodes in the simulation based on a Bayesian rule, wherein execution of the Bayesian module further comprises: generating a binary decision tree representing the chain in the simulation, wherein the chain includes one or more nodes; prioritizing which nodes in the tree to simulate; generating one or more simulations; executing the simulation model with data associated with the prioritized nodes in the tree in parallel to determine a posterior probability for each prioritized node; and determining whether each prioritized node is accepted or rejected based on the posterior probabilities. Numerous other aspects are provided.

    Systems and methods for advanced additive manufacturing
    20.
    发明授权
    Systems and methods for advanced additive manufacturing 有权

    公开(公告)号：US10661552B2

    公开(公告)日：2020-05-26

    申请号：US15663220

    申请日：2017-07-28

    Applicant: General Electric Company

    Inventor： Ananda Barua ,  Arun Karthi Subramaniyan ,  Daniel Jason Erno ,  Darren Lee Hallman

    IPC: B33Y50/02 ,  B33Y10/00 ,  B29C64/153 ,  B33Y30/00 ,  B22F3/105 ,  B33Y50/00 ,  G05B19/4099 ,  G05B19/04 ,  B29C64/20 ,  B29C64/386

    Abstract: A controller for use in an additive manufacturing system including a consolidation device configured to consolidate material is provided. The controller is configured to receive a build file for a component including a plurality of build layers, wherein each build layer includes a component outer perimeter, at least one build layer generating function, at least one generating function variable, and at least one generating function constant. The controller is configured to generate at least one control signal to control a power output throughout at least one scan path of the consolidation device across the material for each build layer of the plurality of build layers, the at least one scan path generated based at least partially on the component outer perimeter, the at least one generating function, the at least one generating function variable, and the at least one generating function constant for each build layer.

Patent Agency Ranking