中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.015 seconds)

    Methods and systems for estimating a remaining useful life of an asset
    1.
    发明授权
    Methods and systems for estimating a remaining useful life of an asset 有权

    公开(公告)号：US12189383B2

    公开(公告)日：2025-01-07

    申请号：US17446708

    申请日：2021-09-01

    Applicant: Ford Global Technologies, LLC

    Inventor： Devesh Upadhyay ,  Huanyi Shui ,  Dimitar Filev

    IPC: G05B23/02 ,  G07C5/00 ,  G07C5/08

    Abstract: Methods and systems are provided for monitoring a health of a vehicle component. In one embodiment, a method is provided, comprising dividing a population of vehicles of a connected vehicle population into a plurality of vehicle classes; for each vehicle class of the plurality of vehicle classes, training a class-specific model of the vehicle class to predict a health status variable of a vehicle component included in the vehicle class based on labelled data from historic databases and calibration data; and for each vehicle class of the plurality of vehicle classes, using a first Federated Learning strategy to request local model data from each vehicle of a plurality of vehicles of the vehicle class; receive the local model data from the plurality of vehicles; update the class-specific model based on the received local model data; and send updated parameters of the class-specific model to vehicles included in the vehicle class.

    SYSTEMS AND METHODS FOR MONITORING AND TRAINING A MANUFACTURING SYSTEM
    2.
    发明公开
    SYSTEMS AND METHODS FOR MONITORING AND TRAINING A MANUFACTURING SYSTEM 审中-公开

    公开(公告)号：US20240231289A1

    公开(公告)日：2024-07-11

    申请号：US18153157

    申请日：2023-01-11

    Applicant: Ford Global Technologies, LLC

    Inventor： Zhiyi Chen ,  Harshal Maske ,  Devesh Upadhyay ,  Huanyi Shui ,  Michael Brendan Hopka ,  Xun Huan

    IPC: G05B13/02 ,  G05B13/04

    CPC classification number: G05B13/027 ,  G05B13/042

    Abstract: A method includes generating, by a given autoencoder, a given operational indicator based on sensor data obtained from one or more sensors disposed at a given manufacturing station; selectively aggregating, by the given linear propagator and based on a linear mapping model, the given operational indicator and one or more additional operational indicators associated with one or more additional manufacturing stations to selectively generate an aggregated operational indicator; generating, by the given neural network and in response to generating the aggregated operational indicator, a predicted operational characteristic of the given manufacturing station based on the given operational indicator and the aggregated operational indicator; and determining a state of the manufacturing system based on the predicted operational characteristic and one or more additional predicted operational characteristics generated by one or more additional neural networks from among the plurality of neural networks.

    Vehicle powertrain control system
    4.
    发明授权
    Vehicle powertrain control system 有权

    公开(公告)号：US11535241B2

    公开(公告)日：2022-12-27

    申请号：US17212470

    申请日：2021-03-25

    Applicant: FORD GLOBAL TECHNOLOGIES, LLC

    Inventor： Yijing Zhang ,  Yuji Fujii ,  Jason Meyer ,  Akshay Bichkar ,  Hirai Jayantilal Haria ,  Huanyi Shui

    IPC: B60W20/40 ,  B60W10/02 ,  B60W10/06

    Abstract: A vehicle includes a transmission, an engine, a clutch, and a controller. The transmission has an input. The engine is configured to generate and deliver torque to the input. The clutch is configured to connect and disconnect the engine from the input, and to crank the engine during an engine start. The controller is programmed to, in response to a command to adjust a torque of the clutch during an engine start and a presence of first condition of the clutch, drive a clutch actuator pressure to a first desired value based on a first transfer function. The controller is further programmed to, in response to a command to adjust the torque of the clutch during the engine start and a presence of a second condition of the clutch, drive the clutch actuator pressure to a second desired value based on a second transfer function.

    Methods and systems for anomaly detection of a vehicle
    7.
    发明授权
    Methods and systems for anomaly detection of a vehicle 有权

    公开(公告)号：US11914358B2

    公开(公告)日：2024-02-27

    申请号：US17446707

    申请日：2021-09-01

    Applicant: Ford Global Technologies, LLC

    Inventor： Devesh Upadhyay ,  Huanyi Shui ,  Dimitar Filev

    IPC: G05B23/02 ,  G07C5/00 ,  H04W4/44

    CPC classification number: G05B23/0283 ,  G05B23/0224 ,  G07C5/006 ,  H04W4/44

    Abstract: Methods and systems are provided for increasing an accuracy of anomaly detection in assets such as vehicle components. In one example, a method provides for continuous health monitoring of connected physical assets, comprising adapting thresholds for anomaly detection and root cause analysis algorithms for the connected assets based on an aggregation of new connected data using machine learning; updating and ranking advanced statistical and machine learning models based on their performance using connected data until confirming a best performing model; and deploying the best performing model to monitor the connected physical assets.

    VEHICLE POWERTRAIN CONTROL SYSTEM
    8.
    发明申请
    VEHICLE POWERTRAIN CONTROL SYSTEM 有权

    公开(公告)号：US20220306080A1

    公开(公告)日：2022-09-29

    申请号：US17212470

    申请日：2021-03-25

    Applicant: FORD GLOBAL TECHNOLOGIES, LLC

    Inventor： Yijing Zhang ,  Yuji Fujii ,  Jason Meyer ,  Akshay Bichkar ,  Hiral Jayantilal Haria ,  Huanyi Shui

    IPC: B60W20/40 ,  B60W10/06 ,  B60W10/02

    Abstract: A vehicle includes a transmission, an engine, a clutch, and a controller. The transmission has an input. The engine is configured to generate and deliver torque to the input. The clutch is configured to connect and disconnect the engine from the input, and to crank the engine during an engine start. The controller is programmed to, in response to a command to adjust a torque of the clutch during an engine start and a presence of first condition of the clutch, drive a clutch actuator pressure to a first desired value based on a first transfer function. The controller is further programmed to, in response to a command to adjust the torque of the clutch during the engine start and a presence of a second condition of the clutch, drive the clutch actuator pressure to a second desired value based on a second transfer function.

    System for query vehicle data
    9.
    发明授权
    System for query vehicle data 有权

    公开(公告)号：US12175804B2

    公开(公告)日：2024-12-24

    申请号：US17547667

    申请日：2021-12-10

    Applicant: FORD GLOBAL TECHNOLOGIES, LLC

    Inventor： Huanyi Shui ,  Zhe Wang ,  Devesh Upadhyay ,  Brandon M. Dawson

    IPC: G07C5/00 ,  G07C5/08

    Abstract: A server includes an interface configured to communicate with a plurality of vehicles; and a processor, programmed to, send a query to the plurality of vehicles, the query identifying types of vehicle data and indicating an initial sampling rate, responsive to receiving the vehicle data sampled by the vehicles, process the vehicle data to obtain a feature result including an estimated value and a variance extending from the estimated value, and responsive to the variance being greater than a first threshold, send a first updated query indicating an increased sampling rate to the plurality of vehicles.

    METHODS AND SYSTEMS FOR ESTIMATING A REMAINING USEFUL LIFE OF AN ASSET
    10.
    发明申请
    METHODS AND SYSTEMS FOR ESTIMATING A REMAINING USEFUL LIFE OF AN ASSET 有权

    公开(公告)号：US20230068432A1

    公开(公告)日：2023-03-02

    申请号：US17446708

    申请日：2021-09-01

    Applicant: Ford Global Technologies, LLC

    Inventor： Devesh Upadhyay ,  Huanyi Shui ,  Dimitar Filev

    IPC: G05B23/02 ,  G07C5/00 ,  G07C5/08

    Abstract: Methods and systems are provided for monitoring a health of a vehicle component. In one embodiment, a method is provided, comprising dividing a population of vehicles of a connected vehicle population into a plurality of vehicle classes; for each vehicle class of the plurality of vehicle classes, training a class-specific model of the vehicle class to predict a health status variable of a vehicle component included in the vehicle class based on labelled data from historic databases and calibration data; and for each vehicle class of the plurality of vehicle classes, using a first Federated Learning strategy to request local model data from each vehicle of a plurality of vehicles of the vehicle class; receive the local model data from the plurality of vehicles; update the class-specific model based on the received local model data; and send updated parameters of the class-specific model to vehicles included in the vehicle class.

Patent Agency Ranking