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
질문

논문 기본 정보

자료유형
학술대회자료
저자정보
김경호 (울산과학기술원) 양상민 (울산과학기술원) 임성훈 (울산과학기술원)
저널정보
대한산업공학회 대한산업공학회 추계학술대회 논문집 2022년 대한산업공학회 추계학술대회
발행연도
2022.11
수록면
2,352 - 2,377 (26page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
Titanium alloy is one of the most widely used materials in various industries, such as aerospace, medical, and automotive industry because of its desirable mechanical properties. However, titanium alloy is also a difficult-to-cut material due to the low thermal conductivity and low specific heat. In particular, in an end milling process using titanium alloy, tool wear influences not only the cutting force but also material removal volume per a single tool as well as the quality of the material surface. Therefore, accurate tool wear prediction is necessary during an end milling process to improve product quality and replace the tool at an appropriate time. Furthermore, because the effects of tool wear prediction on the overall process are significant both in terms of cost and time, uncertainty-aware tool wear prediction should be performed. In this work, a deep learning-based tool wear prediction model, which uses a Bayesian approach, is proposed. First, a CNN-based architecture that integrates multi-scale information extracted from raw sensor measurement data, named deep multi-scale CNN (DMSCNN) is proposed. Second, using a Bayesian approach, DMSCNN is transformed into a probabilistic model that outputs a predictive distribution with uncertainty awareness. Experiments with data collected from the real-world end milling process with three distinct setups have proven the effectiveness of the proposed DMSCNN in tool wear prediction. In addition, Bayesian DMSCNN has shown promising results, outperforming existing comparative deterministic methods, as well as probabilistic methods for tool wear prediction.

목차

등록된 정보가 없습니다.

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

이 논문과 함께 이용한 논문

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-ECN-0101-2023-530-000168733