The applicability of neural network model to predict flow stress for carbon steels
The applicability of neural network model to predict flow stress for carbon steels
复制标题
DOI：
10.1016/s0924-0136(02)01123-8
复制
发表时间：
2003-10
影响因子：
6.3
通讯作者：
M. Phaniraj;Ashok Kumar Lahiri
中科院分区：
文献类型：
--
作者：
M. Phaniraj;Ashok Kumar Lahiri
文献中有许多半经验模型可用于预测钢在热变形过程中的流动应力。近年来，神经网络也得到了应用。这些模型的定量评估表明，在应变率（2 - 120℃−1）、温度（900-1100℃）和应变至0.8的范围内，预测误差范围为平均流动应力的2 - 60%。提出了一种可用于预测0.03 ~ 0.34%C范围内碳钢流变应力的神经网络模型。该网络能够以应变、应变速率、温度和碳当量为输入，模拟流动应力行为，平均误差为平均流动应力的3.7%。该网络不仅能够在应变率和温度域中进行插值，而且还能够在其训练的碳当量域中进行插值。
A number of semi-empirical models are available in literature to predict flow stress of steel during hot deformation. In recent years, neural networks have also been used. Quantitative assessment of these models shows that the prediction errors range from 2 to 60% of the mean flow stress, when used over a range of strain rates (2–120s−1), temperatures (900–1100°C) and strains until 0.8. A neural network model, which can be used to predict flow stress for carbon steels, ranging from 0.03 to 0.34%C, is proposed. The network is able to simulate the flow stress behavior with an average error of 3.7% of the mean flow stress using strain, strain rate, temperature and carbon equivalent as inputs. The network is able to interpolate not only over the domain of strain rates and temperatures but also over the domain of carbon equivalents in which it is trained.