摘要
针对现场在没有出现可见浪形的情况下,利用Shohet判别式设定的出口比例值仍然不能保证在“平坦死区”内,表明该判别式并不能够完全满足现场要求,因此利用神经网络预报精轧F1~F6机架出口比例凸度。利用神经网络来进行预报,与传统模型相比,可以进行高度的非线性模拟,以大量实际数据训练神经网络,具有模型结构简单、容易实现等优点。研究结果表明,在出口厚度为2~6 mm的带钢中,出口凸度均处于±15μm的公差范围内,从而能够满足现场的实际需要。
Considering noticing no visible shape wave, it still could not guarantee export proportion crown in the fiat area according to the Shohet discriminate, which showed that the discriminant could not be applied to the scene. As a result, this paper make use of neural network to forecast export proportion crown from F1 to F6 in the finishing mill. Compared with the traditional analytical model, the neural network has its own advantage, such as highly non-linear simulations, simple and achievable structure because the import variable for training is large amounts of actual data. The resuhs showed that the export proportion crown were all in the range of error ± 15 μm when the thickness of stripe is from 2 to 6 mm, so the neural network could meet the demand of the scene.
出处
《重型机械》
2015年第6期27-31,共5页
Heavy Machinery
基金
中央高校基本科研业务费资助(FRF-TP-14-104A2)
关键词
热轧
板形
比例凸度
神经网络
hot rolling
stripe shape
export proportion crown
neural network