利索-全球专利检索

  1. Login
  2. Sign Up

Search Results

4 records (took 0.011 seconds)

    OIL DEBRIS MONITORING (ODM) WITH ADAPTIVE LEARNING
    2.
    发明公开
    OIL DEBRIS MONITORING (ODM) WITH ADAPTIVE LEARNING 审中-公开
    油污清除监测（ODM）与适应性学习

    公开(公告)号：EP3312604A1

    公开(公告)日：2018-04-25

    申请号：EP17186925.8

    申请日：2017-08-18

    Applicant: United Technologies Corporation

    Inventor： HAGEN, Gregory S. ,  LIN, Yiquing ,  ERDINC, Ozgur ,  GIERING, Michael J. ,  KHIBNIK, Alexander I.

    IPC: G01N33/28 ,  G05B23/02 ,  F16N29/00 ,  F16H57/04

    CPC classification number: G05B23/0289 ,  F01D21/003 ,  F01D25/16 ,  F01D25/18 ,  F05D2220/32 ,  F16H57/0405 ,  F16N29/00 ,  G01N33/2835 ,  G01N33/2858 ,  G05B13/0265 ,  G05B23/0205 ,  G06N99/005

    Abstract: A method (700) for debris particle detection with adaptive learning includes: receiving (705) oil debris monitoring (ODM) sensor data from an oil debris monitor sensor and fleet data from a database; detecting (710) a feature in the ODM sensor data; generating an anomaly detection signal based on detecting (715) an anomaly by comparing the feature in the ODM sensor data to a limit defined by system information stored in the fleet data; selecting (720) a maintenance action request based on the anomaly detection signal; and adjusting one or more of the feature, the anomaly, the limit, and the maintenance action request by applying (725) an adaptive learning algorithm that uses the ODM sensor data, fleet data, and feedback from field maintenance of one or more engines that evolves over time.

    Abstract translation: 一种用于自适应学习的碎片颗粒检测的方法（700）包括：从油碎片监测传感器接收（705）油碎片监测（ODM）传感器数据和来自数据库的队列数据; 检测（710）ODM传感器数据中的特征; 基于通过将ODM传感器数据中的特征与存储在车队数据中的系统信息所限定的限制进行比较来检测（715）异常来生成异常检测信号; 基于所述异常检测信号选择（720）维护动作请求; 以及通过应用（725）自适应学习算法来调整特征，异常，极限和维护动作请求中的一个或多个，所述自适应学习算法使用ODM传感器数据，车队数据和来自一个或多个引擎的现场维护的反馈 随着时间的推移而演变。

    FAULT DETECTION USING HIGH RESOLUTION REALMS
    3.
    发明公开
    FAULT DETECTION USING HIGH RESOLUTION REALMS 审中-公开

    公开(公告)号：EP3401749A1

    公开(公告)日：2018-11-14

    申请号：EP18160262.4

    申请日：2018-03-06

    Applicant: United Technologies Corporation

    Inventor： RIVERA, Linda I. ,  HAGEN, Gregory S. ,  KHIBNIK, Alexander I.

    IPC: G05B23/02

    CPC classification number: G07C5/0816 ,  B64D45/00 ,  B64F5/60 ,  G05B23/0235 ,  G05B23/0245 ,  G08B21/187

    Abstract: An article of manufacture including a tangible, non-transitory computer-readable storage medium having instructions stored thereon for detecting a fault in a gas turbine engine (20) that, in response to execution by a controller (208), cause the controller (208) to perform operations comprising receiving, by the controller (208), a first data output from a first flight data source (202); receiving, by the controller(208), a second data output from a second flight data source (202); determining, by the controller (208), a first flight realm of the first data output based on the second data output; identifying, by the controller (208), a fault threshold using a first parameter of the first flight realm; and comparing, by the controller (208), the first data output to the fault threshold.

Patent Agency Ranking