平滑支持向量模型预测控制集气管压力

Smooth Support Vector Model Predict Control Manifold Pressure

集气管的是炼焦制气的重要组成部分,保持集气管压力的稳定,可以提高炼焦制气的效率,降低炼焦制气中产生的气体对环境的污染。随着数据挖掘理论在工业中的应用,支持向量机(The Support Vector Machine SVM)在集气管压力的控制上取得了良好的效果,但其在处理非线性的数据方面的效果并不显著,为了解决这个问题,这里提出了一种平滑支持向量机模型,这是一个具有数据采集、数据平滑与非线性逼近功能相统一的系统模型,利用平滑度对数据进行噪声处理,将平滑处理过的数据用于回归模型的预测控制。这里提出的方法,对唐山某钢铁企业的实际数据进行实验仿真,结果表明,平滑支持向量模型对集气管压力的控制均方根误差较小,控制效果显著。

The collecting pipe is an important part of coking and gas production,keep the collecting pipe pressure stable,can im⁃prove the efficiency of coking and gas production,reduce the pollution of the gas produced in the coking process to the environment.With the application of data mining theory in industry,The Support Vector Machine(SVM)has achieved good results in the control of tracheal collection pressure.but its effectiveness in dealing with non-linear data is not significant,to solve this problem,This pa⁃per presents a smooth support vector machine model.this is a system model with the functions of data acquisition,data smoothing and nonlinear approximation.smoothness is used for noise processing of data.the smoothed data is used for predictive control of re⁃gression models.The method proposed in this paper is used to simulate the actual data of an iron and steel enterprise in Tangshan.The results show that the root mean square error of the smooth support vector model is small and the control effect is significant.