메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색

논문 기본 정보

자료유형
학위논문
저자정보

최동진 (호서대학교, 호서대학교 대학원)

지도교수
홍선기
발행연도
2021
저작권
호서대학교 논문은 저작권에 의해 보호받습니다.

이용수4

표지
AI에게 요청하기
추천
검색

이 논문의 연구 히스토리 (8)

초록· 키워드

오류제보하기
In order to compensate for the shortcomings of the existing fault diagnosis, fault diagnosis using deep learning is being studied. As a result of these studies, high-accuracy motor fault diagnosis is possible. However, most of these fault diagnostics can only be used in limited environments. In order to learn deep learning, a large amount of various electric motor data is required. However, it is practically impossible to collect all data of electric motors used in the industry. In this study, this problem was solved using K-means and RNN algorithm. Even with this algorithm, it is impossible to diagnose the failure of the motor in the mode environment. Therefore, it is essential to acquire various data. In order to collect this data, a large number of sensors must be attached to the motor and monitored to collect the data. IoT technology was used to collect this data. In addition, a system has been proposed in which a fault diagnosis algorithm is applied to the IoT sensor to monitor the state of the motor while collecting data and supplementing the algorithm based on the collected data.

목차

등록된 정보가 없습니다.

최근 본 자료

전체보기

댓글(0)

0