【作者】 彭艳； 张明； 刘宣亮； 崔金星；

【Author】 Peng Yan;Zhang Ming;Liu Xuanliang;Cui Jinxing;National Engineering Research Center for Equipment and Technology of Cold Strip Rolling, Yanshan University;

【机构】 燕山大学国家冷轧板带装备及工艺工程技术研究中心；

【摘要】 轧机振动是影响轧制过程稳定性的关键因素。本文利用数据挖掘技术研究轧机振动问题,提出基于BP-AdaBoost的轧机振动预测模型和POS-SVM的轧机振动预测模型,并通过某钢厂热连轧系统振动实测数据对两种预测模型进行训练和检验,证明了利用数据挖掘技术能够实现轧机振动的预测;通过比较验证数据,得出POS-SVM轧机振动预测模型预测结果优于BP-AdaBoost轧机振动预测模型;最后分析了轧制工艺参数对轧机振动的影响规律,提出抑振措施,达到了抑振效果。更多还原

【Abstract】 Rolling mill vibration is the key factor affecting the stability of rolling process.In this paper, the data mining technology is used to study the vibration of rolling mills,and two kinds of rolling mill vibration prediction models were established, respectively the vibration mill prediction model based on BP-AdaBoost strong predictor and the rolling mill vibration prediction model based on PSO-SVM algorithm.The two prediction models are trained and tested by the vibration data of a hot rolling mill. It is proved that the vibration prediction of rolling mill can be realized by using data mining technology.By comparison, we can see that the POS-SVM algorithm has better prediction effect.And at the end,by analyzing the influence law of rolling parameters on rolling mill vibration, vibration suppression measures were put forward,and the vibration suppression effect was achieved.更多还原