590 MPa급 고강도강과 6xxx계 알루미늄 합금의 Flow Drilling Screw 접합품질 예측 알고리즘 개발 (Quality Prediction Algorithm for Flow Drilling Screw Joining of 590 MPa High-Strength Steel and 6xxx Series Aluminum Alloy)

서지정보

· 발행기관 : 대한용접접합학회
· 수록지 정보 : 대한용접접합학회지 / 42권 / 4호 / 366 ~ 377페이지
· 저자명 : 최유리, 김동윤, 장준명, 유지영, 이승환

초록

Flow drilling screw (FDS) process is applied to various components such as car bodies and battery cases due to its advantage of enabling one-sided joining. Various studies have been conducted on the correlation between monitored process parameters and joint quality. These correlations suggest the potential for non-destructive classification or prediction of joint quality using process monitoring signals. In this study, the effect of FDS process parameters on joint quality was analyzed, and a decision tree-based quality prediction model for classifying joint quality was developed. The material combination consisted of a 1.8 mm thick SGAFC 590DP as the upper plate and a 3.0 mm thick Al 6061 as the lower plate. To develop the joint quality prediction algorithm, the effect of process parameters in each process step on joint quality was analyzed. It is used as input data to identify various features. The output data were generated by classifying the products into three categories from class 0 to class 2. Based on the extracted feature data, a machine learning algorithm was trained to develop the joint quality prediction model.

영어초록

Flow drilling screw (FDS) process is applied to various components such as car bodies and battery cases due to its advantage of enabling one-sided joining. Various studies have been conducted on the correlation between monitored process parameters and joint quality. These correlations suggest the potential for non-destructive classification or prediction of joint quality using process monitoring signals. In this study, the effect of FDS process parameters on joint quality was analyzed, and a decision tree-based quality prediction model for classifying joint quality was developed. The material combination consisted of a 1.8 mm thick SGAFC 590DP as the upper plate and a 3.0 mm thick Al 6061 as the lower plate. To develop the joint quality prediction algorithm, the effect of process parameters in each process step on joint quality was analyzed. It is used as input data to identify various features. The output data were generated by classifying the products into three categories from class 0 to class 2. Based on the extracted feature data, a machine learning algorithm was trained to develop the joint quality prediction model.

참고자료

· 없음