中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

123 records (took 0.028 seconds)

    System and method for modeling conditional dependence for anomaly detection in machine condition monitoring
    1.
    发明授权
    System and method for modeling conditional dependence for anomaly detection in machine condition monitoring 失效
    在机器状态监测中对异常检测进行条件依赖建模的系统和方法

    公开(公告)号：US08694283B2

    公开(公告)日：2014-04-08

    申请号：US13186538

    申请日：2011-07-20

    Applicant: Chao Yuan

    Inventor： Chao Yuan

    IPC: G06F17/18 ,  G05B17/02

    CPC classification number: G05B17/02 ,  G05B23/0254 ,  G06F11/008

    Abstract: A method for predicting sensor output values of a machine sensor monitoring system includes providing a set of input sensor data X and a set of output sensor data Y for a plurality of sensors the monitor the performance of a machine, learning a functional relationship that maps the input sensor data to the output sensor data by maximizing a logarithm of a marginalized conditional probability function P(Y|X) where a dependence of the output sensor data Y with respect to unknown hidden machine inputs u has been marginalized, providing another set of input sensor data X′, and calculating expected values of the output sensor data Y′ using the input sensor data X′ and the marginalized conditional probability function P(Y|X′), where the calculated expectation values reflect the dependence of the output sensor data Y″ with respect to the unknown hidden machine inputs u.

    Abstract translation: 一种用于预测机器传感器监测系统的传感器输出值的方法包括提供一组输入传感器数据X和用于多个传感器的一组输出传感器数据Y，监视机器的性能，学习映射 通过最大化边缘化条件概率函数P（Y | X）的对数，将传感器数据输入到输出传感器数据，其中输出传感器数据Y相对于未知隐藏机器输入u的依赖已被边缘化，提供另一组输入 传感器数据X'，并且使用输入传感器数据X'和边缘化条件概率函数P（Y | X'）计算输出传感器数据Y'的期望值，其中计算的期望值反映输出传感器数据 Y“相对于未知的隐藏机器输入u。

    CONSUMER BEHAVIORS AT LENDER LEVEL
    2.
    发明申请
    CONSUMER BEHAVIORS AT LENDER LEVEL 有权
    消费者行为水平下降

    公开(公告)号：US20120203688A1

    公开(公告)日：2012-08-09

    申请号：US13450338

    申请日：2012-04-18

    Applicant: Kathleen Haggerty ,  Aashish Prakash ,  Prasanta Sahu ,  Di Xu ,  Chao Yuan

    Inventor： Kathleen Haggerty ,  Aashish Prakash ,  Prasanta Sahu ,  Di Xu ,  Chao Yuan

    IPC: G06Q40/00

    CPC classification number: G06Q40/025 ,  G06Q30/0251 ,  G06Q40/00 ,  G06Q40/02 ,  G06Q40/12

    Abstract: The present disclosure generally relates to financial data processing, and in particular it relates to lender credit scoring, lender profiling, lender behavior analysis and modeling. More specifically, it relates to rating lenders based on data derived from their respective consumers. Also, the present disclosure relates to rating consumer lenders based on the predicted spend capacity of their consumers.

    Abstract translation: 本公开通常涉及财务数据处理，特别涉及放贷人信用评分，贷款人分析，贷款人行为分析和建模。 更具体地说，它涉及基于从各自的消费者得到的数据的评级放债者。 此外，本公开涉及基于消费者预测的消费能力来评估消费者贷方。

    Method and apparatus for improved fault detection in power generation equipment
    5.
    发明授权
    Method and apparatus for improved fault detection in power generation equipment 失效
    发电设备故障检测方法及装置

    公开(公告)号：US07953577B2

    公开(公告)日：2011-05-31

    申请号：US11202861

    申请日：2005-08-12

    Applicant: Chao Yuan ,  Claus Neubauer ,  Zehra Cataltepe

    Inventor： Chao Yuan ,  Claus Neubauer ,  Zehra Cataltepe

    IPC: G06F11/30 ,  G21C17/00

    CPC classification number: G05B23/0254 ,  G05B23/0297

    Abstract: A method and apparatus for detecting faults in power plant equipment is discloses using sensor confidence and an improved method of identifying the normal operating range of the power generation equipment as measured by those sensors. A confidence is assigned to a sensor in proportion to the residue associated with that sensor. If the sensor has high residue, a small confidence is assigned to the sensor. If a sensor has a low residue, a high confidence is assigned to that sensor, and appropriate weighting of that sensor with other sensors is provided. A feature space trajectory (FST) method is used to model the normal operating range curve distribution of power generation equipment characteristics. Such an FST method is illustratively used in conjunction with a minimum spanning tree (MST) method to identify a plurality of nodes and to then connect those with line segments that approximate a curve.

    Abstract translation: 一种用于检测发电厂设备故障的方法和装置公开了使用传感器置信度和一种通过这些传感器测量的识别发电设备的正常工作范围的改进方法。 与传感器相关的残差成比例地分配给传感器的置信度。 如果传感器具有高残留量，那么传感器的信心就很小。 如果传感器具有较低的残留量，则会将高置信度分配给该传感器，并提供该传感器与其他传感器的适当加权。 使用特征空间轨迹（FST）方法对发电设备特性的正常工作范围曲线分布进行建模。 这种FST方法被说明性地与最小生成树（MST）方法一起使用以识别多个节点，然后将它们与近似于曲线的线段连接。

    Incremental learning of nonlinear regression networks for machine condition monitoring
    8.
    发明授权
    Incremental learning of nonlinear regression networks for machine condition monitoring 有权
    用于机器状态监测的非线性回归网络的增量学习

    公开(公告)号：US07844558B2

    公开(公告)日：2010-11-30

    申请号：US11866554

    申请日：2007-10-03

    Applicant: Chao Yuan ,  Claus Neubauer

    Inventor： Chao Yuan ,  Claus Neubauer

    IPC: G06F17/00 ,  G06N5/00

    CPC classification number: G06F11/0751 ,  G05B23/024 ,  G06F11/0706

    Abstract: A method for identifying a potential fault in a system includes obtaining a set of training data. A first kernel is selected from a library of two or more kernels and the first kernel is added to a regression network. A next kernel is selected from the library of two or more kernels and the next kernel is added to the regression network. The regression network is refined. A potential fault is identified in the system using the refined regression network.

    Abstract translation: 用于识别系统中的潜在故障的方法包括获得一组训练数据。 从两个或多个内核的库中选择第一个内核，并将第一个内核添加到回归网络。 从两个或多个内核的库中选择下一个内核，并将下一个内核添加到回归网络。 回归网络细化。 使用精确回归网络在系统中识别出潜在的故障。

    CONSUMER BEHAVIORS AT LENDER LEVEL
    10.
    发明申请
    CONSUMER BEHAVIORS AT LENDER LEVEL 有权
    消费者行为水平下降

    公开(公告)号：US20090248570A1

    公开(公告)日：2009-10-01

    申请号：US12058355

    申请日：2008-03-28

    Applicant: Kathleen Haggerty ,  Aashish Prakash ,  Prasanta Sahu ,  Di Xu ,  Chao Yuan

    Inventor： Kathleen Haggerty ,  Aashish Prakash ,  Prasanta Sahu ,  Di Xu ,  Chao Yuan

    IPC: G06Q40/00

    CPC classification number: G06Q40/02 ,  G06Q20/10 ,  G06Q20/102 ,  G06Q40/00 ,  G06Q40/025 ,  G06Q40/12

    Abstract: The present invention generally relates to financial data processing, and in particular it relates to lender credit scoring, lender profiling, lender behavior analysis and modeling. More specifically, it relates to rating lenders based on data derived from their respective consumers. Also, the present invention relates to rating consumer lenders based on the predicted spend capacity of their consumers.

    Abstract translation: 本发明一般涉及金融数据处理，特别涉及放贷人信用评分，贷款人分析，贷款人行为分析和建模。 更具体地说，它涉及基于从各自消费者得到的数据的评级放债者。 此外，本发明涉及基于消费者预测的消费能力来评估消费者贷款人。

Patent Agency Ranking