中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

12 records (took 0.014 seconds)

    System and method for predicting remaining useful life of component of equipment
    3.
    发明授权
    System and method for predicting remaining useful life of component of equipment 有权

    公开(公告)号：US10262270B2

    公开(公告)日：2019-04-16

    申请号：US15239106

    申请日：2016-08-17

    Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

    Inventor： Hsiang-Tsung Kung ,  Jia-Min Ren ,  Chuang-Hua Chueh ,  Sen-Chia Chang

    IPC: G06N5/04 ,  G06N7/00 ,  G05B23/02 ,  G06N20/00

    Abstract: A system and a method for predicting a remaining useful life (RUL) of a component of an equipment are provided. The system for predicting the RUL of the component of the equipment includes a data acquisition unit, a feature capturing unit, a mapping function generating unit, a similarity analyzing unit and a RUL calculating unit. The feature capturing unit obtains an estimation feature according to a real time sensing record, and obtains a plurality of training features according to a set of history sensing records. The similarity analyzing unit obtains k similar features which are similar to the estimation feature according to the training features. The RUL calculating unit obtains at least one of k predicting information via a mapping function according to the k similar features and calculates an estimation RUL according to at least one predicting value.

    METHOD AND DEVICE OF MEASURING BREAKDOWN STATUS OF EQUIPMENT
    4.
    发明申请
    METHOD AND DEVICE OF MEASURING BREAKDOWN STATUS OF EQUIPMENT 审中-公开

    公开(公告)号：US20170146432A1

    公开(公告)日：2017-05-25

    申请号：US14983033

    申请日：2015-12-29

    Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

    Inventor： Tsung-Jung Hsieh ,  Sen-Chia Chang ,  Yao-Chung Hsu

    IPC: G01M99/00 ,  G06F17/11

    CPC classification number: G01M99/005 ,  G06F17/11

    Abstract: A breakdown measuring method and a breakdown measuring device are disclosed. The breakdown measuring method includes the following steps: capturing a plurality of process flows, each of the process flows includes at least one recipe step; analyzing a flow attribute corresponding to each of the process flows; capturing sensing data corresponding to the at least one recipe step; generating a local feature in a time interval corresponding to each of the process flows according to the corresponding flow attribute, the corresponding at least one recipe step and the corresponding sensing data; generating a trend distribution according to the local features of the process flows; determining whether to send an alarm information based on the trend distribution.

    ELECTRONIC DEVICE AND METHOD FOR TRAINING NEURAL NETWORK MODEL
    6.
    发明申请
    ELECTRONIC DEVICE AND METHOD FOR TRAINING NEURAL NETWORK MODEL 有权

    公开(公告)号：US20230118614A1

    公开(公告)日：2023-04-20

    申请号：US17534340

    申请日：2021-11-23

    Applicant: Industrial Technology Research Institute

    Inventor： Mao-Yu Huang ,  Sen-Chia Chang ,  Ming-Yu Shih ,  Tsann-Tay Tang ,  Chih-Neng Liu

    IPC: G06N3/08 ,  G06N3/04

    Abstract: An electronic device and a method for training a neural network model are provided. The method includes: obtaining a first neural network model and a first pseudo-labeled data; inputting the first pseudo-labeled data into the first neural network model to obtain a second pseudo-labeled data; determining whether a second pseudo-label corresponding to the second pseudo-labeled data matching a first pseudo-label corresponding to the first pseudo-labeled data; in response to the second pseudo-label matching the first pseudo-label, adding the second pseudo-labeled data to a pseudo-labeled dataset; and training the first neural network model according to the pseudo-labeled dataset.

    Methods, devices and non-transitory computer-readable medium for parameter optimization
    9.
    发明授权
    Methods, devices and non-transitory computer-readable medium for parameter optimization 有权

    公开(公告)号：US10929472B2

    公开(公告)日：2021-02-23

    申请号：US15857148

    申请日：2017-12-28

    Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

    Inventor： Po-Yu Huang ,  Hong-Chi Ku ,  Sen-Chia Chang ,  Te-Ming Chen ,  Pei-Yi Lo

    IPC: G06F16/903 ,  G06N5/02 ,  G06N20/00

    Abstract: A parameter optimization method includes: a parameter search is performed on an input parameter, an output response value and a target value through a plurality of optimization schemes to search for a plurality of candidate recommended parameters. Each optimization scheme is assigned to a weight value according to user historical decision information. At least one recommended parameter is selected from the candidate recommended parameters according to the weight values. An user interface is provided for a user to input a decision instruction. A new input parameter is selected from the at least one recommended parameter according to the decision instruction; the new input parameter is inputted into the target system; and a new output response value is evaluated whether meets a specification condition. The user historical decision information is updated based on the decision instruction to adjust the weight values.

    TREE SEARCH-BASED SCHEDULING METHOD AND ELECTRONIC APPARATUS USING THE SAME
    10.
    发明申请
    TREE SEARCH-BASED SCHEDULING METHOD AND ELECTRONIC APPARATUS USING THE SAME 审中-公开

    公开(公告)号：US20190146463A1

    公开(公告)日：2019-05-16

    申请号：US15888096

    申请日：2018-02-05

    Applicant: Industrial Technology Research Institute

    Inventor： Tsung-Jung Hsieh ,  Sen-Chia Chang ,  Yao-Chung Hsu ,  Che-Ming Kuo ,  I-Hsuan Chung

    IPC: G05B19/418 ,  G06F9/54

    Abstract: A tree search-based scheduling method and an electronic apparatus are provided. In the method, multiple order lists are received and a schedule is initialized, wherein each order list includes multiple production operations. In each order list, a first production operation which has not been joined into the schedule yet is selected, such that multiple prior operations are selected. An execution priority of the prior operations is calculated according to multiple dispatching rules, and multiple candidate operations are selected from the prior operations according to the execution priority. Afterwards, the candidate operations are listed as a next operation of the schedule respectively, and a scheduling simulation is performed according to the dispatching rules to obtain multiple scheduling indicators of the candidate operations. Scheduling is performed according to the scheduling indicators.

Patent Agency Ranking