v-ASVR을 이용한 공구라이프사이클 최적화
Tool Lifecycle Optimization using v-Asymmetric Support Vector Regression
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
With the spread of smart manufacturing, one of the key topics of the 4th industrial revolution, manufacturing systems are moving beyond automation to smartization using artificial intelligence. In particular, in the existing automatic machining, a number of machining defects and non-processing occur due to tool damage or severe wear, resulting in a decrease in productivity and an increase in quality defect rates. Therefore, it is important to measure and predict tool life. In this paper, -ASVR (-Asymmetric Support Vector Regression), which considers the asymmetry of -tube and the asymmetry of penalties for data out of -tube, was proposed and applied to the tool wear prediction problem. In the case of tool wear, if the predicted value of the tool wear amount is smaller than the actual value (under-estimation), product failure may occur due to tool damage or wear. Therefore, it can be said that -ASVR is suitable because it is necessary to overestimate. It is shown that even when adjusting the asymmetry of -tube and the asymmetry of penalties for data out of -tube, the ratio of the number of data belonging to -tube can be adjusted with . Experiments are performed to compare the accuracy of various kernel functions such as linear, polynomial. RBF (radialbasis function), sigmoid, The best result isthe use of the RBF kernel in all cases
Abstract
With the spread of smart manufacturing, one of the key topics of the 4th industrial revolution, manufacturing systems are moving beyond automation to smartization using artificial intelligence. In particular, in the existing automatic machining, a number of machining defects and non-processing occur due to tool damage or severe wear, resulting in a decrease in productivity and an increase in quality defect rates. Therefore, it is important to measure and predict tool life. In this paper, -ASVR (-Asymmetric Support Vector Regression), which considers the asymmetry of -tube and the asymmetry of penalties for data out of -tube, was proposed and applied to the tool wear prediction problem. In the case of tool wear, if the predicted value of the tool wear amount is smaller than the actual value (under-estimation), product failure may occur due to tool damage or wear. Therefore, it can be said that -ASVR is suitable because it is necessary to overestimate. It is shown that even when adjusting the asymmetry of -tube and the asymmetry of penalties for data out of -tube, the ratio of the number of data belonging to -tube can be adjusted with . Experiments are performed to compare the accuracy of various kernel functions such as linear, polynomial. RBF (radialbasis function), sigmoid, The best result isthe use of the RBF kernel in all cases
참고문헌 (14)
- Cichosz, P., "Data Mining Algorithms" (2015), Wiley
- Huang, X., "Asymmetric v-tube support vector regression", Computational Statistics and Data Analysis, 77, pp.371~382 (2014)
- 정훈, "기계적 모터 고장진단을 위한 머신러닝 기법", 한국산업경영시스템학회지, 40(1), pp.57~64 (2017), 한국산업경영시스템학회
- Kang, T.H., "Development of a Web-based Analysis Program for Reliability Assessment of Machine Tools", Procee- dings of 2004 The Korean Society of Machine Tool Engineers Fall Conference, pp.369~374 (2004)
- 김길환, "스마트홈 지능형 서비스 플랫폼을 위한 데이터 마이닝 기법에 대한 적합도 평가", 한국산업경영시스템학회지, 40(2), pp.68~77 (2017), 한국산업경영시스템학회
- Kong, D., "Gaussian process re-gression for tool wear prediction", Mechanical Systems and Signal Processing, 104, pp.556~574 (2018)
- 공정식, "유전 알고리즘을 이용한 공구 수명 예측 최적화", 한국산학기술학회논문지, 19(11), pp.338~343 (2018), 한국산학기술학회[DOI]
- 이동주, "일반화 서포트벡터 분위수회귀에 대한 연구", 한국산업경영시스템학회지, 43(4), pp.107~115 (2020), 한국산업경영시스템학회[DOI]
- Ozel, T., "Predictive modeling of surface roughness and tool wear in hard turning using regre- ssion and neural networks", International Journal of Machine Tools and Manufacture, 45(4-5), pp.467~479 (2005)
- Pandiyan, V., "In-process tool condition monitoring in com-pliant abrasive belt grinding process using support vector machine and genetic algorithm", Journal of Manufacturing Processes, 31, pp.199~213 (2018)
- Scholkopf, B., "New support vector algorithms", Neural Com-put, 12(5), pp.1207~1245 (2000)
- Taylor, F. W., "On the Art of Cutting Metals", Trans. ASME, 28, pp.310~350 (1906)
- Wu, D., "A Comparative Study on Machine Lear-ning Algorithms for Smart Manufacturing : Tool Wear Prediction Using Random Forests", Journal of Manu. Sci. and Engineering, 139(7), pp.1~10 (2017)
- Xu, G., "CNC internal data based incremental cost-sensitive support vector machine method for tool breakage monitoring in end milling", Engineering Applications of Artificial Intelligence, 74, pp.90~103 (2018)