期刊
IEEE ACCESS
卷 8, 期 -, 页码 134124-134136出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2020.3010506
关键词
Mechanical factors; Data models; Predictive models; Training; Biological neural networks; Linear programming; Strips; Mechanical property; deep neural network; safe semi-supervised regression; Bayesian optimization; hot-rolled strips
资金
- National Natural Science Foundation of China [U1960202]
- China Postdoctoral Science Foundation [2019M651467]
- Natural Science Foundation Joint Fund Project of Liaoning Province [2019-KF-25-06]
In the present work, to solve the problem of the lacking enough labeled training data for deep learning, a safe semi-supervised regression supporting Bayesian optimization deep neural network (SAFER-BODNN) model was proposed to establish mechanical property prediction model of hot-rolled strips. The Pearson correlation coefficient was applied to reduce the data dimension. The safe semi-supervised regression was implemented to add the pseudo labels to the unlabeled data for training dataset expansion. The deep neural network was trained with Bayesian optimization to determine the optimal hyper-parameters of the network. The results show that the SAFER-BODNN model achieves good performance for mechanical property prediction of hot-rolled strips with correlation coefficient of 0.9610 for yield strength, 0.9682 for tensile strength, and 0.8619 for elongation, respectively. Compared with the deep neural network trained on the labeled dataset, the SAFER-BODNN model obtains stable smaller predicted errors. Among all the variables, C content and Mn content have large influence on the yield strength and tensile strength, coiling temperature has the largest influence on the elongation. The investigation makes full use of unlabeled data to elevate the prediction performance of the deep neural network, and also provides a way for deep learning modeling when the data are insufficient.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据