기계학습 모델 복잡도에 따른 템퍼드 마르텐사이트 경도 예측 정확도 비교 연구 (A Comparative Study of the Accuracy of Machine Learning Models for Predicting Tempered Martensite Hardness According to Model Complexity)

서지정보

· 발행기관 : 대한금속·재료학회
· 수록지 정보 : 대한금속·재료학회지 / 60권 / 9호 / 713 ~ 721페이지
· 저자명 : 전준협, 김동응, 홍준호, 김휘준, 이석재

초록

We investigated various numerical methods including a physical-based empirical equation, linear regression, shallow neural network, and deep learning approaches, to compare their accuracy for predicting the hardness of tempered martensite in low alloy steels. The physical-based empirical equation, which had been previously proposed with experimental data, was labelled and used in the present study. While it had a smaller number of coefficients, the prediction accuracy of the physical-based empirical equation was almost similar to that of the regression model based on the response surface method. The prediction accuracy of the machine learning models clearly improved as the number of layers increased and became more complicated in structure before the model began to overfit. The key point we found was that a single layered neural network model with optimized hyperparameters resulted in similar or better hardness prediction performance compared to deep learning models with a more complex architecture. We also analyzed 18 research papers from the literature which used neural network models to predict the hardness of steels. Only two recent papers adopted a convolutional neural network, as a kind of deep learning model, in a new attempt to predict hardness. The other 16 papers from 1998 to 2021 commonly chose shallow neural network models because a more complicated model is less effective than a simple model for regression problems with well-labeled experimental data in materials science and engineering.

영어초록

We investigated various numerical methods including a physical-based empirical equation, linear regression, shallow neural network, and deep learning approaches, to compare their accuracy for predicting the hardness of tempered martensite in low alloy steels. The physical-based empirical equation, which had been previously proposed with experimental data, was labelled and used in the present study. While it had a smaller number of coefficients, the prediction accuracy of the physical-based empirical equation was almost similar to that of the regression model based on the response surface method. The prediction accuracy of the machine learning models clearly improved as the number of layers increased and became more complicated in structure before the model began to overfit. The key point we found was that a single layered neural network model with optimized hyperparameters resulted in similar or better hardness prediction performance compared to deep learning models with a more complex architecture. We also analyzed 18 research papers from the literature which used neural network models to predict the hardness of steels. Only two recent papers adopted a convolutional neural network, as a kind of deep learning model, in a new attempt to predict hardness. The other 16 papers from 1998 to 2021 commonly chose shallow neural network models because a more complicated model is less effective than a simple model for regression problems with well-labeled experimental data in materials science and engineering.

참고자료

· 없음