公开(公告)号：US20200151610A1

公开(公告)日：2020-05-14

申请号：US16231732

申请日：2018-12-24

Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

Inventor： Chuang-Hua CHUEH ,  Jia-Min REN ,  Po-Yu HUANG ,  Yu-Hsiuan CHANG

IPC: G06N20/20 ,  G06K9/62

Abstract: An ensemble learning prediction method includes: establishing a plurality of base predictors based on a plurality of training data; initializing a plurality of sample weights of a plurality of sample data and initializing a processing set; in each iteration round, based on the sample data and the sample weights, establishing a plurality of predictor weighting functions of the predictors in the processing set and predicting each of the sample data by each of the predictors in the processing set for identifying a prediction result; evaluating the predictor weighting functions, and selecting a respective target predictor weighting function from the predictor weighting functions established in each iteration round and selecting a target predictor from the predictors in the processing set to update the processing set and to update the sample weights of the sample data.

公开(公告)号：US20230153652A1

公开(公告)日：2023-05-18

申请号：US17830040

申请日：2022-06-01

Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

Inventor： Chuang-Hua CHUEH ,  Po-Yu HUANG ,  Shu-Hsuan LIN ,  Yu-Hsiuan CHANG ,  Cheng-Wei CHEN

IPC: G06N5/04 ,  G06N5/02

CPC classification number: G06N5/04 ,  G06N5/022

Abstract: A parameter optimization device includes a data acquisition module, a sampling function calculation module, a clustering module and a parameter recommendation module. The data acquisition module is configured to acquire several input parameter values and corresponding several measurement output values. The sampling function calculation module is configured to obtain several sampling function values according to the input parameter values and the measurement output values. The clustering module is configured to obtain several parameter groups according to the input parameter values and the sampling function values. The parameter recommendation module is configured to obtain several recommended parameter values from at least one of the parameter groups.

公开(公告)号：US20210200196A1

公开(公告)日：2021-07-01

申请号：US16874434

申请日：2020-05-14

Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

Inventor： Hsin-Chi CHEN ,  Chuang-Hua CHUEH ,  Chun-Fang CHEN ,  Chi-Heng LIN ,  Chun-Hsu Chen

IPC: G05B23/02 ,  G05B19/04 ,  G05B19/048

Abstract: A data processing system, including a cyclic correlation establishing module, a data pattern establishing module, and a data pattern alignment module, is provided. The cyclic correlation establishing module receives a plurality of first sensor data, obtained from a first sensor operation performed on processing devices, and receives a table of processing steps and cyclic procedures. The cyclic correlation establishing module obtains a data correlation of the first sensor data according to the number of sample points in a data cycle of the first sensor data and the table to correct the first sensor data. The data pattern establishing module obtains a plurality of first data pattern features from the first sensor data. The data pattern alignment module aligns a plurality of second sensor data obtained from a second sensor operation performed on the processing devices with the first sensor data according to the first data pattern features.

公开(公告)号：US20170161622A1

公开(公告)日：2017-06-08

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 ,  G06N99/00

CPC classification number: G06N5/04 ,  G05B23/0283 ,  G06N7/005 ,  G06N99/005

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.