지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학위논문
- 저자정보
- 지도교수
- 이원균
- 발행연도
- 2021
- 저작권
- 충남대학교 논문은 저작권에 의해 보호받습니다.
이용수1
이 논문의 연구 히스토리 (4)
2021
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
Tool wear monitoring is a key technology for improving productivity of the machine tool by optimizing the replacement period of the tool during machining process. In this paper, we proposed an algorithm to
estimate the tool wear during milling process based on the cutting force measurement and an auto associative neural network (AANN). AANN is suitable for classifying data with complex boundaries because it is relatively free from overfitting problems that can occur in existing artificial neural networks. The wear indicator of the tool was defined using the characteristics of the AANN, and the appropriate characteristics were calculated from the cutting force generated during machining to apply it to tool wear. After the artificial neural network was trained with the data collected during normal milling process, the wear indicator was calculated for all data and compared with other methods which predict flank wear of milling tools.
estimate the tool wear during milling process based on the cutting force measurement and an auto associative neural network (AANN). AANN is suitable for classifying data with complex boundaries because it is relatively free from overfitting problems that can occur in existing artificial neural networks. The wear indicator of the tool was defined using the characteristics of the AANN, and the appropriate characteristics were calculated from the cutting force generated during machining to apply it to tool wear. After the artificial neural network was trained with the data collected during normal milling process, the wear indicator was calculated for all data and compared with other methods which predict flank wear of milling tools.
목차
1. 서론 11.1 연구 동기 및 배경 11.2 연구 개요 및 목표 32. 공구 마모 예측 기법 42.1 다중 선형 회귀 42.2 다층 퍼셉트론 62.3 자가연상신경망 82.3.1 자가연상신경망의 구조 82.3.1 자가연상신경망의 학습 과정 92.3.1 공구 마모 모니터링을 위한 지표 정의 123. 가공 실험 143.1 실험 장치 구성 143.2 절삭력 특성 추출 194. 공구 마모 예측모델 학습 결과 274.1 다중 선형 회귀 274.2 다층 퍼셉트론 314.3 자가연상신경망 354.4 결과 분석 및 비교 395. 결론 42참고문헌 43ABSTRACT 45
최근 본 자료
댓글(0)
0