공구마모 예측을 위한 SVM에서 커널에 대한 연구

• 발행기관: 한국산업경영시스템학회
• 저자명: 최수진 이창용 김치수 이동주
• 간행물 정보: 『한국산업경영시스템학회 학술대회』2019년 추계학술대회 논문집, 149~149쪽, 전체 1쪽
• 주제분류: 공학 > 산업공학
• 파일형태: PDF
• 발행일자: 2019.10.30

영문 초록

It is important for the prediction of tool wear to determine the exact timing of tool replacement in smart factories. Prediction of tool wear was applied with various machine learning techniques such as Random Forest and Artificial Neural Network. In this study, we are going to apply support vector machine technique. one of the machine learning techniques, to predict tool wear and to compare the accuracy of various kernel functions. The results of the experiment showed that the best result was the use of the polynomial kernel in all cases. The second best result was the use of the RBF kernel , and the third best case was the use of linear kernel. The worst accuracy was the use of the sigmoid kernel.

목차

요약

서론

SVM

실험조건

커널에 따른 비교

참고문헌