论文部分内容阅读
为了有效预测双机架炉卷轧机的轧制力,使热轧板带材生产具有很好的可操作性,采用粒子群算法(PSO)优化BP神经网络,建立了往复式双机架炉卷轧机轧制力预测的智能模型。以某钢厂热轧产品Q195实测数据作为试验样本,并将粒子群算法优化的BP神经网络模型和标准BP网络模型分别用于轧制力预测,结果表明PSO-BP神经网络模型在预报精度上明显优于标准BP网络模型,并且PSO-BP神经网络模型预测轧制力的误差率控制在10%以内。
In order to effectively predict the rolling force of a two-stand grate rolling mill and make the strip production of hot-rolled strip have good operability, a particle swarm optimization (PSO) -based BP neural network is used to optimize the reciprocating double- Intelligent Model for Rolling Force Prediction. Taking the measured data of hot rolled product Q195 in a steel mill as the test sample, the BP neural network model and the standard BP network model optimized by particle swarm optimization are respectively used for the prediction of rolling force. The results show that the prediction accuracy of the PSO-BP neural network model Obviously better than the standard BP network model, and PSO-BP neural network model predicts the error rate of rolling force within 10%.