THE METHOD FOR DETECTING FAULT OF MOTOR

Disclosed is a method for detecting a motor winding defect, which comprises: a step of measuring a phase current to acquire one-dimensional current waveform data; a step of using a two-dimensional image generating algorithm to acquire two-dimensional image data based on the one-dimensional current w...

Full description

Saved in:
Bibliographic Details
Main Authors OH HYUN SEOK, JUNG WON HO, LEE KUK HEE
Format Patent
LanguageEnglish
Korean
Published 07.10.2021
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:Disclosed is a method for detecting a motor winding defect, which comprises: a step of measuring a phase current to acquire one-dimensional current waveform data; a step of using a two-dimensional image generating algorithm to acquire two-dimensional image data based on the one-dimensional current waveform data; a step of inputting the two-dimensional image data to an artificial intelligence model to acquire a current characteristic factor vector value; a step of acquiring a defect index based on a distance between the current characteristic factor vector value and a normal characteristic factor vector value; and a step of using the defect index to determine whether there is a winding defect. 본 개시는 전동기 권선 결함 진단 방법에 있어서 상전류를 측정하여 1차원 전류 파형데이터를 획득하는 단계; 2차원 이미지 생성 알고리즘을 이용하여 상기 1차원 전류 파형 데이터에 기초한 2차원 이미지 데이터를 획득하는 단계; 상기 2차원 이미지 데이터를 인공 지능 모델에 입력하여 전류 특성인자 벡터 값을 획득하는 단계; 상기 전류 특성인자 벡터 값과 정상 특성인자 벡터 값의 거리에 기초한 결함지표를 획득하는 단계; 및 상기 결함지표를 이용하여 상기 권선 결함 유무를 판단하는 단계를 개시한다.
Bibliography:Application Number: KR20200073742