论文部分内容阅读
将概率神经网络建模方法与预测思想相结合用于热轧轧制节奏评价,研究并建立了基于PNN神经网络的热轧轧制节奏评价模型。基于涟钢2 250mm热轧厂的实测数据,将建立的PNN网络轧制节奏评价模型用于生产实际,并将结果与BP神经网络进行对比。结果表明,该模型具有便捷、快速、预测精度高、泛化能力强的特点,可代替现有的基于经验公式和经验数据的评价方法,同时为轧制节奏的优化和生产效率的提高提供了参考,具有重要的现实意义。
The probabilistic neural network modeling method and forecasting theory are combined to evaluate the rhythm of hot rolling and the rhythm evaluation model of hot rolling based on PNN neural network is established. Based on the measured data of 2 250 mm hot rolling mill in Lianyuan Iron and Steel Co., Ltd., the established rhythm evaluation model of PNN rolling mill was used in production practice, and the results were compared with BP neural network. The results show that the model has the advantages of convenience, rapidness, high prediction accuracy and generalization ability. It can replace the existing evaluation methods based on empirical formula and empirical data, and at the same time provide the optimization of rolling cadence and the improvement of production efficiency Reference, has important practical significance.