저항 점용접부 형상 및 파단 거동에 대한 머신러닝 모델 및 하이퍼파라미터 최적화 (Machine Learning Modeling and Hyper-Parameter Optimization for Weld Nugget Formation and Failure Behavior of Resistance Spot Welds)

서지정보

· 발행기관 : 대한용접접합학회
· 수록지 정보 : 대한용접접합학회지 / 39권 / 6호 / 658 ~ 665페이지
· 저자명 : 유현정, 김철희

초록

The welding process parameters of resistance spot welding are determined by quality indicators, such as nugget di- ameter, and tensile shear test behavior, such as failure load and location. In this study, deep-learning models were in- vestigated to predict the quality indicators from base materials and process parameter information. For each model, hyperparameters, such as the number of hidden layers, number of nodes in the hidden layer, learning rate of the opti- mizer, and number of epochs, were optimized based on the model performance. The regression models for nugget diameter and failure load showed coefficients of determination of 0.90 and 0.95, respectively. Two models were de- veloped to classify failure location: a 1-step model that estimates the failure location from the base material in- formation and process parameters, and a 2-step model that estimates the failure location from the base material in- formation and the nugget diameter as predicted by the developed regression model. The classification models for failure location showed similar accuracies of approximately 90%.

영어초록

The welding process parameters of resistance spot welding are determined by quality indicators, such as nugget di- ameter, and tensile shear test behavior, such as failure load and location. In this study, deep-learning models were in- vestigated to predict the quality indicators from base materials and process parameter information. For each model, hyperparameters, such as the number of hidden layers, number of nodes in the hidden layer, learning rate of the opti- mizer, and number of epochs, were optimized based on the model performance. The regression models for nugget diameter and failure load showed coefficients of determination of 0.90 and 0.95, respectively. Two models were de- veloped to classify failure location: a 1-step model that estimates the failure location from the base material in- formation and process parameters, and a 2-step model that estimates the failure location from the base material in- formation and the nugget diameter as predicted by the developed regression model. The classification models for failure location showed similar accuracies of approximately 90%.

참고자료

· 없음